Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks130 from public data
- MAT: Mask-Aware Transformer for Large Hole Image Inpainting539
A novel transformer-based model for large hole inpainting is presented, which unifies the merits of transformers and convolutions to efficiently process high-resolution images.
- Video-P2P: Video Editing with Cross-Attention Control391
This work proposes to first tune a Text-to-Set (T2S) model to complete an approximate inversion and then optimize a shared unconditional embedding to achieve accurate video inversion with a small memory cost, and proves that it is crucial for consistent video editing.
- ControlNeXt: Powerful and Efficient Control for Image and Video Generation200
This paper designs a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model, and proposes another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence.
- 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.
- On Efficient Transformer-Based Image Pre-training for Low-Level Vision146
To comprehensively diagnose the influence of pre-training, a whole set of principled evaluation tools are designed that uncover its effects on internal representations, revealing that multi-related-task pre- training is more effective and data-efficient than other alternatives.
- 108
- Best-Buddy GANs for Highly Detailed Image Super-resolution95
This work considers the single image super-resolution (SISR) problem, and proposes best-buddy GANs (Beby-GAN) for rich-detail SISR, a region-aware adversarial learning strategy that directs the model to focus on generating details for textured areas adaptively.
- CoSeR: Bridging Image and Language for Cognitive Super-Resolution93
The Cognitive Super-Resolution (CoSeR) framework is introduced, empowering SR models with the capacity to comprehend low-resolution images and a novel condition injection scheme called “Ali-in-Attention ”, consolidating all conditional information into a single module.
- 90
- Texture Generation on 3D Meshes with Point-UV Diffusion89
Point-UV diffusion, a coarse-to-fine pipeline that marries the denoising diffusion model with UV mapping to generate 3D consistent and high-quality texture images in UV space, is presented.
- 83
- JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration55
JarvisIR, a VLM-powered agent that leverages the VLM as a controller to manage multiple expert restoration models to enhance system robustness, reduce hallucinations, and improve generalizability in real-world adverse weather, is proposed.
- 53
- 52
- 52
- NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer44
This work proposes NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.
- Video Demoiréing with Relation-Based Temporal Consistency43
A relation-based temporal consistency loss is proposed to encourage the model to learn temporal consistency priors directly from ground-truth reference videos, which facilitates producing temporally consistent predictions and effectively maintains frame-level qualities.
- POSTA: A Go-to Framework for Customized Artistic Poster Generation42
This work presents POSTA: a modular framework powered by diffusion models and multimodal large language models for customized artistic poster generation, which demonstrates POSTA’s exceptional controllability and design diversity, outperforming existing models in both text accuracy and aesthetic quality.
- One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation42
This work proposes FluxSR, a novel one-step diffusion Real-ISR technique based on flow matching models that outperforms existing one-step diffusion-based Real-ISR methods and proposes TV-LPIPS as a perceptual loss and Attention Diversification Loss as a regularization term to reduce token similarity in transformer, thereby eliminating high-frequency artifacts.
- Revisiting Temporal Alignment for Video Restoration40
This work presents a novel, generic iterative alignment module which employs a gradual refinement scheme for sub-alignments, yielding more accurate motion compensation and a non-parametric re-weighting method, where the importance of each neighboring frame is adaptively evaluated in a spatial-wise way for aggregation.
- Efficient Real-World Image Super-Resolution Via Adaptive Directional Gradient Convolution38
A novel equivalent parameter fusion method for DGConv is devised that maintains its rich representational capabilities while keeping computational costs consistent with a single Vanilla Convolution (VConv), enabling DGConv to improve the performance of existing super-resolution networks without incurring additional computational expenses.
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning37
This work introduces a novel “Low-Res Leads the Way” (LWay) training framework, merging Supervised Pre-training with Self-supervised Learning to enhance the adaptability of SR models to real-world images.
- MC 2 : Multi-concept Guidance for Customized Multi-concept Generation34
MC2 is proposed, a novel approach for multi-concept customization that enhances flexibility and fidelity through inference-time optimization and can be seamlessly applied to text-to-image generation, providing robust compositional capabilities.
- 34
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.