Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
- Chen Change LoySuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works154 from public data
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks4,943
This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN.
- Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data2,160
This work extends the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data and employs a U-Net discriminator with spectral normalization to increase discriminator capability and stabilize the training dynamics.
- 1,955
- EDVR: Video Restoration With Enhanced Deformable Convolutional Networks1,341
This work proposes a novel Video Restoration framework with Enhanced Deformable convolutions, termed EDVR, and proposes a Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration.
- Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation1,235
This work proposes a new T2V generation setting—One-Shot Video Tuning, where only one text-video pair is presented, and introduces Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy.
- Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform1,224
It is shown that it is possible to recover textures faithful to semantic classes in a single network conditioned on semantic segmentation probability maps through a novel Spatial Feature Transform (SFT) layer that generates affine transformation parameters for spatial-wise feature modulation.
- Activating More Pixels in Image Super-Resolution Transformer1,170
A novel Hybrid Attention Transformer (HAT) is proposed, which combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability.
- MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing902
MasaCtrl converts existing self-attention in diffusion models into mutual self-attention, so that it can query correlated local contents and textures from source images for consistency, and proposes a mask-guided mutual self-attention strategy.
- 881
- BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond698
A succinct pipeline is shown that achieves appealing improvements in terms of speed and restoration quality in comparison to many state-of-the-art algorithms and can serve as strong baselines for future VSR approaches.
- Towards Real-World Blind Face Restoration with Generative Facial Prior676
This work proposes GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration that achieves superior performance to prior art on both synthetic and real-world datasets.
- MotionCtrl: A Unified and Flexible Motion Controller for Video Generation673
MotionCtrl is presented, a unified and flexible motion controller for video generation designed to effectively and independently control camera and object motion and is a relatively generalizable model that can adapt to a wide array of camera poses and trajectories once trained.
- VideoCrafter1: Open Diffusion Models for High-Quality Video Generation633
This model is the first open-source I2V foundation model capable of transforming a given image into a video clip while maintaining content preservation constraints, and can generate realistic and cinematic-quality videos with a resolution of $1024 \times 576.
- FateZero: Fusing Attentions for Zero-shot Text-based Video Editing594
F FateZero, a zero-shot text-based editing method on real-world videos without per-prompt training or use-specific mask, is proposed, which is the first one to show the ability of zero-shot text-driven video style and local attribute editing from the trained text-to-image model.
- Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild372
This work introduces SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up, and develops a restoration-guided sampling method to suppress the fidelity issue encountered in generative-based restoration.
- 370
- Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models334
This paper proposes a new framework called Mix-of-Show, which adopts an embedding-decomposed LoRA (ED-LoRA) for single-client tuning and gradient fusion for the center node to preserve the in-domain essence of single concepts and support theoretically limitless concept fusion.
- GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution305
This work shows that pre-trained Generative Adversarial Networks (GANs), e.g., StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor image super-resolution (SR) and shows clear improvements in terms of fidelity and texture faithfulness in comparison to existing methods.
- From Persona to Personalization: A Survey on Role-Playing Language Agents291
A comprehensive survey of RPLAs, illustrating the evolution and recent progress in RPLAs integrating with cutting-edge LLM technologies and categorizing personas into three types: 1) Demographic Persona, which leverages statistical stereotypes; 2) Character Persona, focused on well-established figures; and 3) Individualized Persona, customized through ongoing user interactions for personalized services.
- DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models241
A novel image editing method, DragonDiffusion, enabling Drag-style manipulation on Diffusion models, that can transform the editing signals into gradients via feature correspondence loss to modify the intermediate representation of the diffusion model.
- Making LLaMA SEE and Draw with SEED Tokenizer227
SEED is introduced, an elaborate image tokenizer that empowers LLMs with the ability to SEE and Draw at the same time, and with SEED tokens, LLM is able to perform scalable multimodal autoregression under its original training recipe, i.e., next-word prediction.
- VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution216
An automatic and scalable pipeline to collect a high-quality video face dataset (VFHQ), which contains over 16, 000 high-fidelity clips of diverse interview scenarios, and shows that the temporal information plays a pivotal role in eliminating video consistency issues as well as further improving visual performance.
- SmartEdit: Exploring Complex Instruction-Based Image Editing with Multimodal Large Language Models213
A Bidirectional Interaction Module (BIM) is proposed that enables comprehensive bidirectional information interactions between the input image and the MLLM output and demonstrates that a small amount of complex instruction editing data can effectively stimulate SmartEdit’ s editing capabilities for more complex instructions.
- Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models209
This paper makes the first attempt to introduce explicit 3D shape priors into the CLIP-guided 3D optimization process, and proposes to jointly optimize a learnable text prompt and fine-tune the text-to-image diffusion model for rendering-style image generation.
- FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling205
This work proposes FreeNoise, a tuning-free and time-efficient paradigm to enhance the generative capabilities of pretrained video diffusion models while preserving content consistency, and designs a novel motion injection method to support the generation of videos conditioned on multiple text prompts.
- Understanding Deformable Alignment in Video Super-Resolution195
It is shown that deformable convolution can be decomposed into a combination of spatial warping and convolution, which reveals the commonality of deformable alignment and flow-based alignment in formulation, but with a key difference in their offset diversity.
- HAT: Hybrid Attention Transformer for Image Restoration179
A new Hybrid Attention Transformer (HAT) is proposed that combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages, and achieves state-of-the-art performance both quantitatively and qualitatively.
- Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval177
Considering the enormous computational overhead of incorporating all historical context, the Memory Retrieval module is proposed to select truly relevant context frames by determining FOV overlap between camera poses, which significantly reduces the number of candidate frames without substantial information loss.
- Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance166
This paper explores customized video generation by utilizing text as context description and motion structure (e.g., frame-wise depth) as concrete guidance as concrete guidance in joint-conditional video generation using a Latent Diffusion Model.
- MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions164
This work proposes MiraData, a high-quality video dataset that surpasses previous ones in video duration, caption detail, motion strength, and visual quality, and introduces MiraBench, which enhances existing benchmarks by adding 3D consistency and tracking-based motion strength metrics.
- Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners152
This work proposes a mul-timodality latent aligner with the pre-trained ImageBind model that shares a similar core as the clas-sifier guidance that guides the diffusion denoising process during inference time, and shows the superior performance of the method on joint video-audio generation, visual-steered audio generation, and audio-steered vi-sual generation tasks.
- ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models150
This work investigates the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes and proposes the dispersed convolution and noise-damped classifier-free guidance, which can enable ultra-high-resolution image generation.
- Planting a SEED of Vision in Large Language Model150
This study identifies two crucial principles for the architecture and training of SEED that effectively ease subsequent alignment with LLMs, and emphasizes the great potential of discrete visual tokens in versatile multimodal LLMs and the importance of proper image tokenizers in broader research.
- Robust Reference-based Super-Resolution via C 2 -Matching149
The proposed C2-Matching significantly outperforms state of the arts by over 1dB on the standard CUFED5 benchmark and shows great generalizability on WR-SR dataset as well as robustness across large scale and rotation transformations.
- GameFactorly: Creating New Games with Generative Interactive Videos142
This paper addresses the fundamental challenge of action controllability by introducing GF-Minecraft, an action-annotated game video dataset without human bias, and developing an action control module that enables precise control over both keyboard and mouse inputs, and proposes a multi-phase training strategy with a domain adapter that decouples game style learning from action control.
- 135
- Rethinking Alignment in Video Super-Resolution Transformers135
This work proposes a new and efficient alignment method called patch alignment, which aligns image patches instead of pixels in VSR Transformers, which could demonstrate state-of-the-art performance on multiple benchmarks.
- Towards Vivid and Diverse Image Colorization with Generative Color Prior135
This work aims at recovering vivid colors by leveraging the rich and diverse color priors encapsulated in a pretrained Generative Adversarial Networks (GAN) via a GAN encoder and incorporating these features into the colorization process with feature modulations.
- Path-Restore: Learning Network Path Selection for Image Restoration118
The results show that Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region is effective for real-world denoising, where the noise distribution varies across different regions on a single image.
- Deep Network Interpolation for Continuous Imagery Effect Transition116
This work proposes a simple yet universal approach to attain a smooth control of diverse imagery effects in many low-level vision tasks, including image restoration, image-to-image translation, and style transfer through linear interpolation in the parameter space of two or more correlated networks.
- DreamDiffusion: Generating High-Quality Images from Brain EEG Signals111
Quantitative and qualitative results demonstrate the effectiveness of the proposed DreamDiffusion method as a significant step towards portable and low-cost ``thoughts-to-image'', with potential applications in neuroscience and computer vision.
- Can Large Language Models Understand Real-World Complex Instructions?110
This work proposes CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically, design eight features for complex instructions and construct a comprehensive evaluation dataset from real-world scenarios.
- 107
- Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation106
This work develops a framework comprised of two functional modules, which provides video candidates with desired scene or motion context described by query texts, and generates plot-aligned videos under the guidance of motion structure and text prompts.
- SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints104
This work proposes a plug-and-play module that enhances a pre-trained text-to-video model for multi-camera video generation, ensuring consistent content across different viewpoints, and introduces a multi-view synchronization module to maintain appearance and geometry consistency across these viewpoints.
- Positional Encoding as Spatial Inductive Bias in GANs97
This work shows that SinGAN's impressive capability in learning internal patch distribution, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators, and proposes a new multi-scale training strategy and demonstrates its effectiveness in the state-of-the-art unconditional generator StyleGAN2.
- KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases94
By integrating LLMs with KBs, KnowledGPT properly answers a broader range of questions requiring world knowledge compared with vanilla LLMs, utilizing both knowledge existing in widely-known KBs and extracted into personalized KBs.
- ToonCrafter: Generative Cartoon Interpolation86
A novel approach that transcends traditional correspondence-based cartoon video interpolation, paving the way for generative interpolation, and designs a toon rectification learning strategy that seamlessly adapts live-action video priors to the cartoon domain, resolving the domain gap and content leakage issues.
- 85
- Interactive Story Visualization with Multiple Characters84
A system for generic interactive story visualization, capable of handling multiple novel characters and supporting the editing of layout and local structure is proposed, developed by leveraging the prior knowledge of large language and T2I models, trained on massive corpora.
- Inserting Anybody in Diffusion Models via Celeb Basis83
Empowered by the proposed celeb basis, the new identity in the customized model showcases a better concept combination ability than previous personalization methods and can also learn several new identities at once and interact with each other where the previous customization model fails to.
- CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation81
To overcome the scarcity of in-the-wild datasets with 3D object motion and camera pose annotations, this work carefully establish an automated data annotation pipeline that extracts 3D bounding boxes and camera trajectories from large-scale video data.
- 3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation76
3DTrajMaster is introduced, a robust controller that regulates multi-entity dynamics in 3D space, given user-desired 6DoF pose (location and rotation) sequences of entities and sets a new state-of-the-art in both accuracy and generalization for controlling multi-entity 3D motions.
- CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation70
Giving-circumstance acting for training and evaluating role-playing LLMs is introduced, where LLMs sequentially portray multiple characters in book scenes, and state-of-the-art performance surpassing or matching GPT-4o on evaluation and three existing benchmarks are exhibited.
- Temporally consistent video colorization with deep feature propagation and self-regularization learning67
A novel temporally consistent video colorization (TCVC) framework that effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of colorization and introduces a self-regularization learning (SRL) scheme to minimize the differences in predictions obtained using different time steps.
- DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models67
Equipped with the DeSRA, the cause and characteristics of the GAN artifacts produced in unseen test data without ground-truths are analyzed and artifacts from inference are eliminated and the ability of SR models to be applied in real-world scenarios is improved.
- 66
- VideoTetris: Towards Compositional Text-to-Video Generation62
The proposed VideoTetris is a novel framework that enables compositional T2V generation, equipped with a new reference frame attention mechanism to improve the consistency of auto-regressive video generation.
- Towards A Better Metric for Text-to-Video Generation61
This paper investigates the limitations inherent in existing metrics and introduces a novel evaluation pipeline, the Text-to-Video Score (T2VScore), which integrates two pivotal criteria: Text-Video Alignment, which scrutinizes the fidelity of the video in representing the given text description, and Video Quality, which evaluates the video's overall production caliber with a mixture of experts.
- MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution61
A metric learning strategy to map the unquantifiable degradation levels in real-world scenarios to a metric space, which is trained in an unsupervised manner and introduces an anchor point strategy in the metric learning process to normalize the distribution of metric space.
- RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization57
A new re-parameterizable block tailored for SR, namely RepSR, which consists of a clean residual path and two expand-and-squeeze convolution paths with the modified BN and can achieve a better trade-off between performance and actual running time than previous SR methods.
- StyleAdapter: A Unified Stylized Image Generation Model52
The StyleAdapter is proposed, a unified stylized image generation model capable of producing a variety of stylized images that match both the content of a given prompt and the style of reference images, without the need for per-style fine-tuning.
- CamCloneMaster: Enabling Reference-based Camera Control for Video Generation51
This work proposes CamCloneMaster, a framework that enables users to replicate camera movements from reference videos without requiring camera parameters or test-time fine-tuning, and presents the Camera Clone Dataset, a large-scale synthetic dataset designed for camera clone learning, encompassing diverse scenes, subjects, and camera movements.
- StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter50
StyleCrafter is introduced, a generic method that enhances pre-trained T2V models with a style control adapter, enabling video generation in any style by providing a reference image, and designs a scale-adaptive fusion module to balance the influences of text-based content features and image-based style features.
- OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer48
This paper designs a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively, and proposes Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples.
- 47
- 47
- AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos46
The proposed method, AnimeSR, is capable of restoring real-world low-quality animation videos effectively and efficiently, achieving superior performance to previous state-of-the-art methods.
- 45
- 44
- Unifying Image Processing as Visual Prompting Question Answering44
Inspired by NLP question answering techniques, PromptGIP treats the input-output image pair as a structured question-answer sentence, thereby reprogramming the image processing task as a prompting QA problem, eliminating the need for task-specific finetuning.
- NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results41
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video and proposed the LDV 2.0 dataset, which includes theLDV dataset (240 videos) and 95 additional videos.
- 41
- Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control40
RoboMaster is presented, a novel framework that models inter-object dynamics via a collaborative trajectory formulation and decomposes the interaction process into three sub-stages: pre-interaction, interaction, and post-interaction, and models each phase using the dominant object.
- NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results40
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022, and the competition set-up, datasets, proposed methods and their results.
- Ischemia - Reperfusion injury: A roadmap to precision therapies39
Developing personalized treatment plans tailored to different cell types holds promise for overcoming existing therapeutic bottlenecks, significantly improving patient outcomes, and providing new directions for addressing the challenges of I/R injury.
- Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis37
It is found that improving the reconstruction fidelity of VQ tokenizers does not necessarily improve the generation, instead, learning to compress semantic features within VQ tokenizers significantly improves generative transformers' ability to capture textures and structures.
- 36
- GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond36
The method, Generative LatEnt bANk (GLEAN), goes beyond existing practices by directly leveraging rich and diverse priors encapsulated in a pre-trained GAN, and extends to different tasks including image colorization and blind image restoration.
- 34
- MultiShotMaster: A Controllable Multi-Shot Video Generation Framework34
This work extends a pretrained single-shot model of RoPE by integrating two novel variants of RoPE, and introduces Multi-Shot Narrative RoPE, which applies explicit phase shift at shot transitions, enabling flexible shot arrangement while preserving the temporal narrative order.
- CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models34
The CustomNet is introduced, a novel object customization approach that explicitly incorporates 3D novel view synthesis capabilities into the object customization process, and facilitates zero-shot object customization without test-time optimization, offering simultaneous control over the viewpoints, location, and background.
- 32
- Composite Photograph Harmonization with Complete Background Cues28
This work investigates the usage of a target background and finds that a complete background plays a vital role in both seamlessly blending and harmonization and develops a network to learn the composition process given an imperfect alpha matte with appearance features extracted from the complete background to adjust color distribution.
- A Survey of Interactive Generative Video27
This paper defines IGV as a technology that combines generative capabilities to produce diverse high-quality video content with interactive features that enable user engagement through control signals and responsive feedback, and proposes a comprehensive framework that decomposes an ideal IGV system into five essential modules.
- 26
- SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model26
A novel framework of SphereDiffusion is introduced to address the unique challenges of spherical distortion and geometry characteristics, for better generating high-quality and precisely controllable spherical panoramic images.
- 26
- 26
- Reference-based Image and Video Super-Resolution via $C^{2}$-Matching25
A contrastive correspondence network, which learns transformation-robust correspondences using augmented views of the input image, and a dynamic aggregation module to address the potential misalignment issue between input images and reference images are designed.
- 24
- X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model24
X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules to work directly with the upgraded text-to-image diffusion model without further retraining, is introduced and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.
- SketchVideo: Sketch-based Video Generation and Editing21
This paper proposes a memory-efficient control structure with sketch control blocks that predict residual features of skipped DiT blocks that achieves superior performance in controllable video generation and editing of real or synthetic videos.
- AnimateZero: Video Diffusion Models are Zero-Shot Image Animators21
This work proposes AnimateZero to unveil the pre-trained text-to-video diffusion model, i.e., AnimateDiff, and provide more precise appearance and motion control abilities for it, and demonstrates the effectiveness of the proposed method in both T2V and related applications.
- 17
- 16
- 15
- MINDECHO: Role-Playing Language Agents for Key Opinion Leaders15
This paper introduces MINDECHO, a comprehensive framework for the development and evaluation of KOL RPLAs, and evaluates the effectiveness of MINDECHO in developing and evaluating KOL RPLAs.
- 15
- 14
- 14
- Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs13
This paper introduces Chain-of-Knowledge, a comprehensive framework for knowledge reasoning, including methodologies for both dataset construction and model learning, and enhances CoK with a trial-and-error mechanism that simulates the human process of internal knowledge exploration.
- VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning12
VFXMaster is introduced, a unified, reference-based framework for VFX video generation that recasts effect generation as an in-context learning task, enabling it to reproduce diverse dynamic effects from a reference video onto target content and demonstrates remarkable generalization to unseen effect categories.
- Image Conductor: Precision Control for Interactive Video Synthesis11
Image Conductor, a method for precise control of camera transitions and object movements to generate video assets from a single image, is proposed, and a trajectory-oriented video motion data curation pipeline for training is developed.
- SurveyAgent: A Conversational System for Personalized and Efficient Research Survey11
SurveyAgent is introduced, a novel conversational system designed to provide personalized and efficient research survey assistance to researchers that stands out by offering a unified platform that supports researchers through various stages of their literature review process, facilitated by a conversational interface that prioritizes user interaction and personalization.
- CustomNet: Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models10
CustomNet is presented, a unified encoder-based object customization framework that explicitly incorporates 3D novel view synthesis capabilities into the customization process, and outperforms other customization methods regarding identity preservation, diversity, and harmony.
- RelightMaster: Precise Video Relighting with Multi-plane Light Images8
This work proposes RelightMaster, a novel framework for accurate and controllable video relighting, and introduces Multi-plane Light Image (MPLI), a novel visual prompt inspired by Multi-Plane Image (MPI).
- Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation8
This work presents Any2Caption, a novel framework for controllable video generation under any condition that interprets diverse inputs into dense, structured captions that offer backbone video generators with better guidance.
- 8
- Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models8
This work presents Story3D-Agent, a pioneering approach that leverages the capabilities of LLMs to transform provided narratives into 3D-rendered visualizations, and enables precise control over multi-character actions and motions, as well as diverse decorative elements, ensuring the long-range and dynamic 3D representation.
- Hybrid Warping Fusion for Video Frame Interpolation8
This work explicitly investigates the warping step and proposes a way to combine the strength from using both forward and backward warping, and introduces hybrid warping fusion for frame interpolation.
- FaceFormer: Scale-aware Blind Face Restoration with Transformers8
A novel scale-aware blind face restoration framework, named FaceFormer, which formulates facial feature restoration as scale- aware transformation as well as dynamically generates upsampling filters based on the original scale-factor priors, which facilitate the network to adapt to arbitrary face scales.
- SemanticGen: Video Generation in Semantic Space7
SemanticGen is introduced, a novel solution to address limitations by generating videos in the semantic space by directly modeling a vast set of low-level video tokens using bi-directional attention and observing that generation in the semantic space leads to faster convergence compared to the VAE latent space.
- PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution7
An innovative approach to utilizing video diffusion priors for patch-wise VSR, which integrates a dual-stream adapter for conditional guidance, and can achieve highly competitive 4K VSR based on a 512×512 resolution base model, with extremely high efficiency.
- Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos7
A Temporal Consistency Network (TCN) cooperated with alignment smoothing to reduce jitters and flickers in restored videos is proposed, a flexible component that can be seamlessly plugged into the most advanced face image restoration algorithms, ensuring the quality of image-based restoration is maintained as closely as possible.
- 6
- 6
- SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution5
This work establishes a simple yet effective baseline for cascaded video super-resolution generation, offering practical insights to guide future advancements in efficient cascaded synthesis systems.
- 5
- 5
- InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews5
- 5
- 4
- Improved hybrid estimation of distribution algorithm for distributed parallel assembly permutation flow shop scheduling problem4
An improved hybrid distribution estimation algorithm that adopts a single‐layer permutation encoding and decoding strategy based on the rule of the Earliest Finished Time is proposed to solve the distributed parallel assembly permutation flow shop scheduling problem.
- Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks3
It is suggested that a robust world model should not be a loose collection of capabilities but a normative framework that integrally incorporates interaction, perception, symbolic reasoning, and spatial representation.
- OpenWorldLib: A Unified Codebase and Definition of Advanced World Models3
This paper introduces OpenWorldLib, a comprehensive and standardized inference framework for Advanced World Models, and proposes a clear definition: a world model is a model or framework centered on perception, equipped with interaction and long-term memory capabilities, for understanding and predicting the complex world.
- 3
- SiamMFF: UAV Object Tracking Algorithm Based on Multi-Scale Feature Fusion3
A SiamMFF tracking method that introduces an efficient multi-scale feature fusion strategy and replaces the ordinary convolution with deformable convolution to increase the sense field of convolution operation to enhance the feature extraction capability is proposed.
- 3
- Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling2
DeScore is a training-efficient and generalizable video reward model that independently refines CoT reasoning quality and calibrates the final reward, ensuring that higher-quality reasoning directly translates to superior model performance.
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Vera: Identity-Faithful Human Subject-to-Video Generation–
Vera is proposed, a unified human-centric S2V framework for single- and multi- person generation that improves human identity consistency, multi-person subject binding, and motion naturalness, while reducing identity confusion and excessive reference-image copying.
- –
- –
- –
- –
- –
- A Reason-then-Describe Instruction Interpreter for Controllable Video Generation–
ReaDe is proposed, a universal, model-agnostic interpreter that converts raw instructions into precise, actionable specifications for downstream video generators that offers a practical route to aligning controllable video generation with accurately interpreted user intent.
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.