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
- Chen Change LoySuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works41 from public data
- 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.
- Exploiting Diffusion Prior for Real-World Image Super-Resolution715
A novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution by employing the time-aware encoder can achieve promising restoration results without altering the pre-trained synthesis model, thereby preserving the generative prior and minimizing training cost.
- 709
- 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.
- BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment687
This study redesigns BasicVsr by proposing second-order grid propagation and flow-guided deformable alignment, and shows that by empowering the re-current framework with enhanced propagation and align-ment, one can exploit spatiotemporal information across misaligned video frames more effectively.
- 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.
- ProPainter: Improving Propagation and Transformer for Video Inpainting267
This work introduces dual-domain propagation that combines the advantages of image and feature warping, exploiting global correspondences reliably, and proposes a mask-guided sparse video Transformer, which achieves high efficiency by discarding unnecessary and redundant tokens.
- 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.
- 191
- Investigating Tradeoffs in Real-World Video Super-Resolution185
A stochastic degradation scheme that reduces up to 40% of training time without sacrificing performance is proposed and it is suggested that employing longer sequences rather than larger batches during training allows more effective uses of temporal information, leading to more stable performance during inference.
- 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.
- 134
- ReVersion: Diffusion-Based Relation Inversion from Images101
This work proposes the Relation Inversion task, which aims to learn a specific relation (represented as “relation prompt”) from exemplar images and proposes a novel “relation-steering contrastive learning” scheme to steer the relation prompt towards relation-dense regions, and disentangle it away from object appearances.
- Instruct-Imagen: Image Generation with Multi-modal Instruction98
Human evaluation on various image generation datasets re-veals that Instruct-Imagen matches or surpasses prior task-specific models in-domain and demonstrates promising generalization to unseen and more complex tasks.
- 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.
- 45
- 44
- NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results43
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results, and gauge the state of the art of video quality enhancement.
- DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models41
This paper proposes a two-step approach DreamInpainter, which employs a discriminative token selection module to eliminate redundant subject details, preserving the subject's identity while allowing changes according to other conditions such as mask shape and text prompts.
- 41
- Dual Associated Encoder for Face Restoration36
This work proposes a novel dual-branch framework named DAEFR, which introduces an auxiliary LQ branch that extracts crucial information from the LQ inputs and incorporates association training to promote effective synergy between the two branches, enhancing code prediction and output quality.
- 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.
- NTIRE 2021 Challenge on Video Super-Resolution36
This paper presents evaluation results from two competition tracks as well as the proposed solutions to the NTIRE 2021 Challenge on Video Super-Resolution, and develops conventional video SR methods focusing on the restoration quality.
- On the Generalization of BasicVSR++ to Video Deblurring and Denoising33
The proposed framework achieves compelling performance with great efficiency in various video restoration tasks including video deblurring and denoising and achieves comparable performance to Transformer-based approaches with up to 79% of parameter reduction and 44x speedup.
- 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.
- Multi-task Image Restoration Guided By Robust DINO Features24
It is observed that the features of DINOv2 can effectively model semantic information and are independent of degradation factors, and a multi-task image restoration approach leveraging robust features extracted from DINOv2 to solve multi-task image restoration simultaneously is proposed.
- A Simple Approach to Unifying Diffusion-based Conditional Generation19
This work introduces a simple, unified framework to handle diverse conditional generation tasks involving a specific image-condition correlation, and demonstrates that multiple models can be effectively combined for multi-signal conditional generation.
- Re-Boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration16
A self-collaboration (SC) strategy for existing restoration models is proposed, achieving significant performance improvement without increasing the framework’s inference complexity.
- Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance10
This work shows that through constructing a subject-agnostic condition and applying their proposed dual classifier-free guidance, one could obtain outputs consistent with both the given subject and input text prompts, and demonstrates its applicability in second-order customization methods, where an encoder-based model is fine-tuned with DreamBooth.
- Identity Encoder for Personalized Diffusion10
This work learns an identity encoder which can extract an identity representation from a set of reference images of a subject, together with a diffusion generator that can generate new images of the subject conditioned on the identity representation.
- HoliSDiP: Image Super-Resolution via Holistic Semantics and Diffusion Prior9
HoliSDiP is presented, a framework that leverages semantic segmentation to provide both precise textual and spatial guidance for diffusion-based Real-ISR through reduced prompt noise and enhanced spatial control.
- KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities7
This work proposes KITTEN, a benchmark for Knowledge-Inensive image generaTion on real-world ENtities, and conducts a systematic study of the latest text-to-image models and retrieval-augmented models, focusing on their ability to generate real-world visual entities, such as landmarks and animals.
- A Convex Model for Edge-Histogram Specification with Applications to Edge-Preserving Smoothing4
This paper directly considers the image gradients and proposes a convex model based on them that allows us to compute the output image efficiently using either Alternating Direction Method of Multipliers or Fast Iterative Shrinkage-Thresholding Algorithm.
- From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition3
This work proposes a simple yet effective method to extend existing models for smooth and consistent attribute transitions, through introducing frame-wise guidance during the denoising process, and presents the Controlled-Attribute-Transition Benchmark (CAT-Bench), which integrates both attribute and motion dynamics.
- AdaIR: Exploiting Underlying Similarities of Image Restoration Tasks with Adapters3
AdaIR is proposed, a novel framework that enables low storage cost and efficient training without sacrificing performance and achieves outstanding results on multi-task restoration while utilizing significantly fewer parameters and less training time.
- CoCoIns: Consistent Subject Generation via Contrastive Instantiated Concepts1
This work introduces Contrastive Concept Instantiation (CoCoIns), a framework that effectively synthesizes consistent subjects across multiple independent generations and proposes a contrastive learning approach that trains the network to distinguish between different combinations of prompts and latent codes.
- Effective Adapter for Face Recognition in the Wild1
This paper proposes an effective adapter for augmenting existing face recognition models trained on high-quality facial datasets using two similar structures, one fixed and the other trainable, to process both the unrefined and enhanced images using two similar structures.
- 1
- –
- –
- –
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 2026-10-10. 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. You will be asked to sign in.