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
- Baining GuoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works51 from public data
- Neural Aggregation Network for Video Face Recognition409
This NAN is trained with a standard classification or verification loss without any extra supervision signal, and it is found that it automatically learns to advocate high-quality face images while repelling low-quality ones such as blurred, occluded and improperly exposed faces.
- GAN Prior Embedded Network for Blind Face Restoration in the Wild387
This work proposes a new method by first learning a GAN for high-quality face image generation and embedding it into a U-shaped DNN as a prior decoder, then fine-tuning the GAN prior embedded DNN with a set of synthesized low- quality face images.
- All-frequency rendering of dynamic, spatially-varying reflectance235
This work describes a technique for real-time rendering of dynamic, spatially-varying BRDFs in static scenes with all-frequency shadows from environmental and point lights and accounts for macro-scale shadowing using a new, nonlinear visibility representation based on spherical signed distance functions (SSDFs).
- 168
- HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment153
HiFaceGAN, a multi-stage framework containing several nested CSR units that progressively replenish facial details based on the hierarchical semantic guidance extracted from the front-end content-adaptive suppression modules, is presented.
- Pocket reflectometry147
A new algorithm for BRDF reconstruction is developed which works directly on these LDR responses, without knowing the light or camera position, or acquiring HDR lighting, and extends the basic algorithm to also recover varying surface normals.
- Global illumination with radiance regression functions127
The approach is to exploit the nonlinear coherence of the indirect illumination data to make the RRF both compact and fast to evaluate, which enables real-time rendering with full global illumination effects, including changing caustics and multiple-bounce high-frequency glossy interreflections.
- Image based relighting using neural networks126
A regression-based method for relighting realworld scenes from a small number of images that approximates matrix segments using neural networks that model light transport as a non-linear function of light source position and pixel coordinates.
- 113
- Active Boundary Loss for Semantic Segmentation110
Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.
- DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders106
This work proposes DDColor, an end-to-end method with dual decoders for image colorization that establishes correlations between color and multi-scale semantic representations via cross-attention, significantly alleviating the color bleeding effect.
- NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results94
The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.
- DiffuEraser: A Diffusion Model for Video Inpainting81
DiffuEraser is introduced, a video inpainting model based on stable diffusion, designed to fill masked regions with greater details and more coherent structures, and outperforms state-of-the-art techniques in both content completeness and temporal consistency while maintaining acceptable efficiency.
- PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning68
This work proposes a reinforcement learning framework to train an AI agent that assists users in exploring the design space efficiently and generating well-optimized storylines and introduces PlotThread, an authoring tool that integrates a set of flexible interactions to support easy customization of storyline visualizations.
- Attention-guided Temporally Coherent Video Object Matting48
A novel deep learning-based video object matting method that can achieve temporally coherent matting results by designing a novel loss term to train the attention weights, which drastically boosts the video matting performance.
- Noise-resistant Deep Metric Learning with Ranking-based Instance Selection45
A noise-resistant training technique for DML, which is named Probabilistic Ranking-based Instance Selection with Memory (PRISM), which identifies noisy data in a minibatch using average similarity against image features extracted by several previous versions of the neural network.
- Towards Fine-Grained Human Pose Transfer With Detail Replenishing Network42
This work develops a more challenging yet practical HPT setting, termed as Fine-grained Human Pose Transfer (FHPT), with a higher focus on semantic fidelity and detail replenishment, and builds up a complete suite of fine- grained evaluation protocols to address the challenges of FHPT in a comprehensive manner.
- DreaMoving: A Human Video Generation Framework based on Diffusion Models35
DreaMoving can generate a video of the target identity moving or dancing anywhere driven by the posture sequences, and a Video ControlNet for motion-controlling and a Content Guider for identity preserving are proposed.
- 31
- Design guidelines for augmenting short-form videos using animated data visualizations31
Results indicate that the proposed guidelines can significantly improve the videos accompanied with data visualizations and help novices easily obtain desired knowledge when augmenting videos.
- FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Look-Up Table30
An efficient pipeline named FastLLVE is proposed that leverages the Look-Up-Table (LUT) technique to maintain inter-frame brightness consistency effectively and can process 1,080p videos at 50+ Frames Per Second (FPS), which is 2 X faster than SOTA CNN-based methods in inference time, making it a promising solution for real-time applications.
- Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach26
A new approach to synthesizing realistic image restoration training pairs using the emerging denoising diffusion probabilistic model (DDPM), which can be used to train robust models for real-world image restoration tasks, such as blind face image restoration and blind image super-resolution.
- RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters24
A white-box framework for photo retouching using parallel region-specific filters, called RSFNet, which employs linear summations of filters, allowing for a more diverse range of filter classes that can be trained more easily.
- Narrative Transitions in Data Videos23
This work proposes a taxonomy of transitions in data videos, where two transition categories are defined in building fluent narratives by using visual variables, and examines how these transitions help make connections between contexts.
- Layout Style Modeling for Automating Banner Design23
A novel style transfer technique is invented so that creating a multi-size style becomes as easy as designing a single banner, and a robust and easy-to-use layout style model is built, upon which the banner design is automated.
- 17
- 15
- SmartShots: An Optimization Approach for Generating Videos with Data Visualizations Embedded14
An optimization method is proposed and developed called SmartShots, which facilitates the automatic integration of in-video visualizations and aims to address two challenges: embedding visualizations while considering both contextual relevance and aesthetic principles and generating videos by assembling multi-media materials.
- LIST: low illumination scene text detector with automatic feature enhancement12
This work adopts a lightweight and non-reference low-light scene text image synthesis network to acquire adequate training data through pixel-wisely adjusting the dynamic range curve of normal-light images and proposes a Low Illumination Scene Text Detector training with authentic synthetic data and integrating dedicated feature enhancement modules.
- Image Aesthetics Assessment Via Learnable Queries10
The IAA-LQ approach adapts learnable queries to extract aesthetic features from pre-trained image features obtained from a frozen image encoder, beating the best state-of-the-art method by 2.2% and 2.1% in terms of SRCC and PLCC, respectively.
- VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models7
VideoElevator is introduced, a training-free and plug-and-play method, which elevates the performance of T2V using superior capabilities of T2I, and facilitates stylistic video synthesis with personalized T2I.
- A Mechanistic View on Video Generation as World Models: State and Dynamics6
This work proposes a novel taxonomy centered on two pillars: State Construction and Dynamics Modeling, which categorize state construction into implicit paradigms (context management) and explicit paradigms (latent compression), while dynamics modeling is analyzed through knowledge integration and architectural reformulation.
- Improving Diffusion-Based Image Restoration with Error Contraction and Error Correction6
Experimental results for image restoration tasks such as super-resolution, Gaussian deblurring, and motion deblurring demonstrate that the proposed diffusion-based image restoration with error contraction and error correction (DiffECC) method can reconstruct high-quality images compared with state-of-the-art sampling-based diffusion models.
- Generating Engaging Promotional Videos for E-commerce Platforms (Student Abstract)6
An algorithm called Shot Composition, Selection and Plotting (ShotCSP) is proposed, which generates visual storylines leveraging film-making principles to improve viewing experience and perceived persuasiveness.
- ChromaFusionNet (CFNet): Natural Fusion of Fine-Grained Color Editing4
ChromaFusionNet (CFNet), a novel approach that views the color fusion problem through the lens of image color inpainting, is presented, paving the way for advancements in the domain of fine-grained color editing.
- 4
- 4
- An AI-empowered Visual Storyline Generator4
Visual Storyline Generator is outlined, an artificial intelligence (AI)-empowered system that automatically generates visual storylines based on a set of images and video footages provided by the user, designed to produce engaging and persuasive promotional videos with an easy-to-use interface.
- 3
- SmartShots: Enabling Automatic Generation of Videos with Data Visualizations Embedded3
A computational framework that integrates non-verbal video clips, images, a melody, and a data table to create a video with data visualizations embedded and a set of post-editing interactions to incorporate users' design knowledge and help them re-edit the automatically-generated videos.
- Personalized Video Summarization with Idiom Adaptation3
This paper presents a domain specific video summarization application with idiom adaptation that leverages multimedia content analysis and insights from cinematic and persuasive domains and validated the effectiveness of the demonstration on a TVC data-set with over 600 videos.
- MovingColor: Seamless Fusion of Fine-grained Video Color Enhancement2
Both quantitative and subjective evaluations validate the effectiveness of MovingColor in delivering state-of-the-art spatio-temporal consistency for video color enhancements, adhering closely to the intended color editing operations.
- 2
- Deep Video Decaptioning2
This paper proposes a generic framework for video decaptioning, which consists of a caption mask extraction network and a frame-attention-based decaptioning network that can accurately remove subtitles from videos in real time, and outperforms the state-of-the-art approaches.
- Domain Specific and Idiom Adaptive Video Summarization2
This work proposes a domain specific and idiom adaptive video summarization approach which first segments the input video and extracts high-level information from each segment, and uses max margin learning to identify the importance of the idioms and metrics in different domains.
- Multi-modal Learnable Queries for Image Aesthetics Assessment1
This paper proposes MMLQ, which utilizes multi-modal learnable queries to extract aesthetics-related features from multi-modal pre-trained features, and achieves new state-of-the-art performance on multimodal IAA.
- 1
- Capturing Piecewise SVBRDFs with Content Aware Lighting1
The method first evaluates the piecewise material distribution over the surface from an image taken with uniform lighting and then finds an suitable 2D light pattern according to the material’s spatial distribution, which combines both step edge and gradient lighting patterns.
- –
- GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation–
GenColor, a novel diffusion-based framework for sophisticated, texture-preserving color enhancement, is proposed, which reframes the task as conditional image generation and learns advanced color transformations that adapt to diverse lighting and content.
- –
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 2026-10-14. 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.