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
Is this you? Claim this profile to confirm or dismiss it.
Works35 from public data
- Scale-Recurrent Network for Deep Image Deblurring1,338
A Scale-recurrent Network (SRN-DeblurNet) is proposed and shown to produce better quality results than state-of-the-arts, both quantitatively and qualitatively in single image deblurring.
- Detail-Revealing Deep Video Super-Resolution574
This paper shows that proper frame alignment and motion compensation is crucial for achieving high quality results, and proposes a “sub-pixel motion compensation” (SPMC) layer in a CNN framework that can generate visually and quantitatively high-quality results, superior to current state-of-the-arts, without the need of parameter tuning.
- 424
- 267
- Deep Automatic Portrait Matting248
An automatic image matting method for portrait images that does not need user interaction is proposed and achieves comparable results with state-of-the-art methods that require specified foreground and background regions or pixels.
- 228
- MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution199
The MASA network for RefSR is proposed, where two novel modules are designed to address the problems of high-quality correspondence matching and the computational cost by a coarse-to-fine correspondence matching scheme.
- MuCAN: Multi-correspondence Aggregation Network for Video Super-Resolution185
This work proposes a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-cor correspondence aggregation scheme to explore self-similarity of images across scales.
- Koala-36M : A Large-Scale Video Dataset Improving Consistency between Fine-Grained Conditions and Video Content156
This work introduces Koala-36M, a large-scale, high-quality video dataset featuring accurate temporal splitting, detailed captions, and superior video quality, and develops a Video Training Suitability Score (VTSS) that integrates multiple sub-metrics, allowing us to filter high-quality videos from the original corpus.
- 140
- 117
- VCNet: A Robust Approach to Blind Image Inpainting86
This paper proposes a two-stage visual consistency network (VCN), meant to estimate where to fill (via masks) and generate what to fill and repairs these estimated missing regions using a new spatial normalization, enabling VCN to be robust to the mask prediction errors.
- Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling62
This paper proposes to compute the temporal difference between frames and divide those pixels into two subsets according to the level of difference and demonstrates the effectiveness of the proposed method and its favorable performance against state-of-the-art methods.
- Inverse Kernels for Fast Spatial Deconvolution50
This work proposes an efficient spatial deconvolution method that can incorporate sparse priors to suppress noise and visual artifacts and is based on estimating inverse kernels that are decomposed into a series of 1D kernels.
- Break Ames room illusion48
A solution based on small-scale defocus blur inherent in optical lens is proposed and it incorporates a matching prior with the newly constructed edgelet dataset using a non-local scheme, and includes semantic depth order cues for physically based inference.
- Facelet-Bank for Fast Portrait Manipulation43
A model based on an end-to-end convolutional neural network that supports fast inference, edit-effect control, and quick partial-model update is proposed that can handle a wide range of expressions, accessories, and makeup effects.
- Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?40
A comprehensive and complex benchmark that evaluates both composition and reasoning capabilities of T2I models, formulating a 12-dimensional evaluation taxonomy and curating each prompt with higher compositional density for composition and greater reasoning intensity for reasoning.
- Zero-Order Reverse Filtering39
A novel strategy to understand general filter via contraction mappings on a metric space is presented and a very simple yet effective zero-order algorithm is proposed, able to practically reverse most filters with low computational cost.
- Motion Inversion for Video Customization37
This work introduces Motion Embeddings, a set of explicit, temporally coherent embeddings derived from a given video, designed to integrate seamlessly with the temporal transformer modules of video diffusion models, modulating self-attention computations across frames without compromising spatial integrity.
- 32
- 29
- 28
- 27
- 25
- DeViT22
Experimental results demonstrate that the Deformed Vision Transformers architecture outperforms previous state-of-the-art methods in quality and quantity and achieves a new state- of- the-art for video inpainting.
- Attribute-Driven Spontaneous Motion in Unpaired Image Translation18
This paper proposes the spontaneous motion estimation module, along with a refinement part, to learn attribute-driven deformation between source and target domains, and achieves promising results in unpaired-image translation tasks, and enable interesting applications based on spontaneous motion.
- Scene-Generalizable Interactive Segmentation of Radiance Fields16
A novel SGISRF method is proposed, which can perform 3D object segmentation for novel (unseen) scenes represented by radiance fields, guided by only a few interactive user clicks in a given set of multi-view 2D images.
- 16
- 15
- Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons15
This work proposes a novel generative adversarial network utilizing weak supervision in the form of pairwise comparisons (PC-GAN) for image attribute editing that can estimate attribute rating efficiently and demonstrate robust performance in noise resistance.
- High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits13
The regional correspondence is used to handle textureless regions in matching and make the CRF system computationally efficient.
- Regional foremost matching for internet scene images11
This work proposes regional foremost matching to reject outlier matching points while still producing dense high-quality correspondence in the remaining foremost regions.
- Feature Decoupling-Recycling Network for Fast Interactive Segmentation9
The Feature Decoupling-Recycling Network (FDRN) is proposed, which decouples the modeling components based on their intrinsic discrepancies and then recycles components that can be reused for each user interaction to improve the efficiency of the whole interactive process.
- Particularity Beyond Commonality: Unpaired Identity Transfer with Multiple References2
This paper proposes a new multi-reference identity transfer framework by simultaneously making use of particularity and commonality of reference through a semantic pyramid alignment module to make proper use of geometric information for individual images.
- –
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.