Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks82 from public data
- Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering1,011
This work introduces Scaffold-GS, which uses an-chor points to distribute local 3D Gaussians, and predicts their attributes on-the-fly based on viewing direction and distance within the view frustum, and effectively reduces redun-dant Gaussians while delivering high-quality rendering.
- Extract Free Dense Labels from CLIP856
The finding suggests that MaskCLIP can serve as a new reliable source of supervision for dense prediction tasks to achieve annotation-free segmentation in pixel-level dense prediction, specifically in semantic segmentation.
- Detecting Visual Relationships with Deep Relational Networks529
The proposed Deep Relational Network is a novel formulation designed specifically for exploiting the statistical dependencies between objects and their relationships and achieves substantial improvement over state-of-the-art on two large data sets.
- CameraCtrl: Enabling Camera Control for Text-to-Video Generation496
Experimental results demonstrate the effectiveness of CameraCtrl in achieving precise camera control with different video generation models, marking a step forward in the pursuit of dynamic and customized video storytelling from textual and camera pose inputs.
- Towards Diverse and Natural Image Descriptions via a Conditional GAN482
A new framework based on Conditional Generative Adversarial Networks (CGAN) is proposed, which jointly learns a generator to produce descriptions conditioned on images and an evaluator to assess how well a description fits the visual content.
- FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding467
FineGym is a new dataset built on top of gymnasium videos that provides temporal annotations at both action and sub-action levels with a three-level semantic hierarchy and systematically investigates different methods on this dataset and obtains a number of interesting findings.
- Temporal Pyramid Network for Action Recognition466
A generic Temporal Pyramid Network (TPN) at the feature-level is proposed, which can be flexibly integrated into 2D or 3D backbone networks in a plug-and-play manner and shows consistent improvements over other challenging baselines on several action recognition datasets.
- Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation458
This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images and allows the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN.
- LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models426
The incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data and proves that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes.
- Generative Diffusion Prior for Unified Image Restoration and Enhancement385
This work proposes the Generative Diffusion Prior (GDP) to effectively model the posterior distributions in an unsupervised sampling manner, and systematically explores a protocol of conditional guidance, which is verified more practical than the commonly used guidance way.
- DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior353
DiffBIR decouples blind image restoration problem into two stages: degradation removal and information regeneration, and proposes IRControlNet, a region-adaptive restoration guidance that can modify the denoising process during inference without model re-training, allowing users to balance realness and fidelity through a tunable guidance scale.
- 351
- BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering333
BungeeNeRF is introduced, a progressive neural radiance field that achieves level-of-detail rendering across drastically varied scales and its support for high-quality rendering in different levels of detail is demonstrated.
- AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views287
This work introduces AnySplat, a feed-forward network for novel-view synthesis from uncalibrated image collections that greatly reduces rendering latency compared to optimization-based neural fields, bringing real-time novel-view synthesis within reach for unconstrained capture settings.
- Self-Supervised Scene De-Occlusion194
This paper makes the first attempt to address the problem of scene de-occlusion through a novel and unified framework that recovers hidden scene structures without ordering and amodal annotations as supervisions, via Partial Completion Network (PCNet)-mask (M) and -content (C), that learn to recover fractions of object masks and contents, respectively, in a self-supervised manner.
- Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation169
This work proposes a novel framework named Hierarchical Audio-to-Gesture (HA2G) for co-speech gesture generation, and develops a contrastive learning strategy based on audio-text alignment for better audio representations.
- 151
- Unsupervised 3D Shape Completion through GAN Inversion150
The proposed ShapeInversion uses a GAN pre-trained on complete shapes by searching for a latent code that gives a complete shape that best reconstructs the given partial input, and is capable of incorporating the rich prior captured in a well-trained generative model.
- Accelerating Diffusion Models via Early Stop of the Diffusion Process142
This work proposes a principled acceleration strategy, referred to as Early-Stopped DDPM (ES-DDPM), which obtains promising acceleration effect and performance improvement over representative baseline methods and demonstrates several attractive properties, including being orthogonal to existing acceleration methods, as well as simultaneously enabling both global semantic and local pixel-level control in image generation.
- DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering131
This work presents DNA-Rendering, a large-scale, high-fidelity repository of human performance data for neural actor rendering, and provides a large-scale and quantitative benchmark in full-scale, with multiple tasks to evaluate the existing progress of novel view synthesis, novel pose animation synthesis, and novel identity rendering methods.
- 125
- Move Forward and Tell: A Progressive Generator of Video Descriptions121
This work proposes a new approach, which produces a descriptive paragraph by assembling temporally localized descriptions by selecting a sequence of distinctive clips and generating sentences thereon in a coherent manner given a video.
- LN3Diff++: Scalable L atent N eural Fields D iffusion for Speedy 3D Generation117
A novel framework, LN3Diff++, designed to bridge the gap and facilitate fast, high-quality, and versatile conditional 3D generation and surpasses existing 3D diffusion methods in inference speed, requiring no per-instance optimization.
- Scene-aware Generative Network for Human Motion Synthesis103
This paper proposes a new framework, which factorizes the distribution of human motions into a distribution of movement trajectories conditioned on scenes and that of body pose dynamics conditioned on both scenes and trajectories, and derives a GAN-based learning approach.
- Recursive Visual Sound Separation Using Minus-Plus Net95
This paper proposes a novel framework, referred to as MinusPlus Network (MP-Net), for the task of visual sound separation, which obtains state-of-the-art results on two large scale datasets, across mixtures with different types and numbers of sounds.
- Intra- and Inter-Action Understanding via Temporal Action Parsing91
This study shows that a sport activity usually consists of multiple sub-actions and that the awareness of such temporal structures is beneficial to action recognition, and investigates a number of temporal parsing methods, and devise an improved method that is capable of mining sub- actions from training data without knowing the labels of them.
- EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion90
The proposed EpiDiff is a localized interactive multiview diffusion model to insert a lightweight epipolar attention block into the frozen diffusion model, leveraging epipolar constraints to enable cross-view interaction among feature maps of neighboring views.
- Point Cloud Pre-Training with Diffusion Models82
This paper considers the point cloud pre-training task as a conditional point-to-point gen-eration problem and introduces a conditional point genera-tor that aggregates the features extracted by the backbone and employs them as the condition to guide the point-to-point recovery from the noisy point cloud, thereby assisting the backbone in capturing both local and global geometric priors as well as the global point density distri-bution of the object.
- Visually Informed Binaural Audio Generation without Binaural Audios81
This work proposes PseudoBinaural, an effective pipeline that is free of binaural recordings, and shows great stability in cross-dataset evaluation and achieves comparable performance under subjective preference.
- Interactive Character Control with Auto-Regressive Motion Diffusion Models72
This work proposes A-MDM (Auto-regressive Motion Diffusion Model), a conditional diffusion model that generates successive motion frames conditioned on the previous frame, and introduces a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning.
- EdgeSAM: Prompt-In-the-Loop Distillation for SAM71
The approach involves distilling the original ViT-based SAM image encoder into a purely CNN-based architecture, better suited for edge devices, and incorporates a lightweight module within the encoder, which achieves a 37-fold speed increase compared to the original SAM.
- TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing67
This work proposes TransEditor, a novel Transformer-based framework to enhance interaction in a dual-space GAN for more controllable editing, and develops a new dual- space editing and inversion strategy to provide additional editing flexibility.
- 61
- 56
- 54
- Neural Network Encapsulation54
The proposed EncapNet performs favorably better against previous state-of-the-arts on CIFAR10/100, SVHN and a subset of ImageNet and an add-on to send back higher capsules as feedback is devised, achieving the optimal transport divergence between two distributions.
- GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation43
A novel 3D generation framework that addresses challenges with input formats, latent space design, and output representations, and incorporates a cascaded latent diffusion model for improved shape-texture disentanglement, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space.
- Improving GANs with A Dynamic Discriminator42
A comprehensive empirical study confirms that the proposed training strategy, termed as DynamicD, improves the synthesis performance without incurring any additional computation cost or training objectives and is synergistic to other discriminator-improving approaches, and brings continuous performance gain when combined for learning GANs.
- DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters36
This work proposes DRiVE, a novel framework for generating and rigging 3D human characters with intricate structures that utilizes a 3D Gaussian representation, facilitating efficient animation and high-quality rendering.
- Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production34
VDS is presented to allow users storyboarding shots in virtual environments, where the filming staff can easily test the settings of shots before the actual filming, demonstrating its efficiency, effectiveness, and great potential in assisting amateur video production.
- 34
- 33
- 30
- 28
- 27
- 27
- PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios26
The framework facilitates the generation of a wide range of human motions, contributing to greater re-alism and adaptability in pedestrian simulations for driving scenarios and significantly enhance both the diver-sity of simulated human motion within the given scenario and the controllability of the content, including language-based control.
- Rethinking the Form of Latent States in Image Captioning26
This work visually reveals the internal dynamics in the process of caption generation, as well as the connections between input visual domain and output linguistic domain, using two-dimensional maps to encode latent states in RNNs.
- 20
- HyperStyle3D: Text-Guided 3D Portrait Stylization via Hypernetworks19
This paper proposes a novel method, dubbed HyperStyle3D, based on 3D-aware GANs for 3D portrait stylization, which offers a strong capacity to handle multiple styles with a single model, but also enables flexible fine-grained stylization that affects only texture, shape, or local part of the portrait.
- 3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping19
3DHumanGAN is a 3D-aware generative adversarial network that synthesizes photo-like images of full-body humans with consistent appearances under different view-angles and body-poses and can incorporate the 3D human prior and enable pose conditioning.
- 19
- 18
- 17
- 3D Data Augmentation for Driving Scenes on Camera16
This work proposes a 3D data augmentation approach termed Drive-3DAug, aiming at augmenting the driving scenes on camera in the 3D space, and modify the original NeRF by introducing a geometric rectified loss and a symmetric-aware training strategy.
- Correspondence Distillation from NeRF-Based GAN14
This paper exploits the rich semantics and structural priors encapsulated in a pre-trained NeRF-based GAN to build dense correspondences across different NeRFs of the same category, which can effectively enable many NeRF-based downstream applications such as texture transfer.
- Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes13
Virtualized 3D Gaussians (V3DG), a cluster-based LOD solution that constructs hierarchical 3D Gaussian clusters and dynamically selects only the necessary ones to accelerate rendering speed, is proposed.
- Revisiting the Evaluation of Image Synthesis with GANs13
This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models, and makes in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
- 13
- 12
- Boosting 3D object generation through PBR materials12
This work proposes a novel approach to boost the quality of generated 3D objects from the perspective of Physics-Based Rendering (PBR) materials, leveraging Stable Diffusion fine-tuned on synthetic data to extract these values and adopting a semi-automatic process to provide room for interactive adjustment.
- CinePreGen: Camera Controllable Video Previsualization via Engine-powered Diffusion12
This work introduces CinePreGen, a visual previsualization system enhanced with engine-powered diffusion that reduces development viscosity, meets users' needs for extensive control and iteration in the design process, and outperforms other AI video production workflows in cinematic camera movement.
- Proc-Gs: Procedural Building Generation for City Assembly with 3D Gaussians11
Drawing inspiration from procedural modeling techniques used in the gaming and visual effects industry, Proc-GS integrates procedural code into the 3D Gaussian Splatting framework, offering a flexible, efficient, and scalable framework for city assembly with high-fidelity and precise control.
- 10
- ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation9
Experiments show that ARTDECO delivers interactive performance comparable to SLAM, robustness similar to feed-forward systems, and reconstruction quality close to per-scene optimization, providing a practical path toward on-the-fly digitization of real-world environments with both accurate geometry and high visual fidelity.
- OrthoPlanes: A Novel Representation for Better 3D-Awareness of GANs9
This work proposes a hybrid explicit-implicit representation called OrthoPlanes, which encodes fine-grained 3D information in feature maps that can be efficiently generated by modifying 2D StyleGANs.
- 8
- 8
- 5
- ChatDyn: Language-Driven Multi-Actor Dynamics Generation in Street Scenes5
ChatDyn is introduced, the first system capable of generating interactive, controllable and realistic participant dynamics in street scenes based on language instructions, and significantly outperforms previous methods on subtasks.
- E2EAI: End-to-End Deep Learning Framework for Active Investing5
This paper is the first to propose an E2E approach that encompasses nearly the entire process of factor investing, including factor selection, combination, stock selection, and portfolio construction, and provides a comprehensive solution for managing multi-task learning conflicts in the context of deep learning-based factor investing.
- Factor Investing with a Deep Multi-Factor Model5
A novel deep multi-factor model is developed that adopts industry neutralization and market neutralization modules with clear financial insights that help to build a dynamic and multi-relational stock graph in a hierarchical structure.
- 4
- 2
- 2
- 2
- $$E^{3}DGE$$: Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion1
This paper addresses the challenge of 3D GAN inversion, focusing on predicting a latent code from a single 2D image to faithfully recover 3D shapes and textures, and introduces an efficient self-training scheme that does not rely on real-world 2D-3D pairs but instead utilizes proxy samples generated from a 3D GAN.
- Learning Modulated Transformation in GANs1
Modulated transformation module (MTM) is equipped in generative adversarial networks with a plug-and-play module, based on which the convolution operation can be applied at variable locations for different instances, and hence offers the model an additional degree of freedom to handle geometry deformation.
- Generative Diffusion Prior for Unified Image and Video Restoration & Enhancement–
Experimental results demonstrate that GDP outperforms leading unsupervised methods across diverse benchmarks in both reconstruction accuracy and perceptual quality, while demonstrating robust generalization to images and videos of any size.
- –
- –
- –
Publication data from OpenAlex; 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.