activity
20232026
most citedTMP: Temporal Motion Propagation for Online Video Super-Resolution

10 citations · 23 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV2026

PixRestore: Unified Image Restoration via Pixel Diffusion Transformer

Lingchen Sun, Rongyuan Wu, Xiangtao Kong +6

Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt l…

cs.CV2026

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?

Lingchen Sun, Rongyuan Wu, Zhengqiang Zhang +4

Recent works such as REPA have shown that guiding diffusion models with external semantic features (e.g., DINO) can significantly accelerate the training of diffusion transformers…

cs.CV2024★ 1 cited

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

Ruihuang Li, Zhengqiang Zhang, Chenhang He +3

Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods…

cs.CV2024

SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing

Ruihuang Li, Liyi Chen, Zhengqiang Zhang +3

Text-based 2D diffusion models have demonstrated impressive capabilities in image generation and editing. Meanwhile, the 2D diffusion models also exhibit substantial potentials for…

eess.IV2024★ 7 cited

Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution

Lingchen Sun, Rongyuan Wu, Jie Liang +3

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However,…

cs.CV2023

Toward Accurate and Temporally Consistent Video Restoration from Raw Data

Shi Guo, Jianqi Ma, Xi Yang +2

Denoising and demosaicking are two fundamental steps in reconstructing a clean full-color video from raw data, while performing video denoising and demosaicking jointly, namely VJD…