13 papers
HarnessIR: Harnessing Multimodal Foundation Models for Universal Real-World Image Restoration
Xiangtao Kong, Shuaizheng Liu, Rongyuan Wu +6
Real-world low-quality images suffer from complex mixed degradations, including but not limited to noise, blur, atmospheric effects, etc. Recent agentic methods usually model real-…
Two Halves are More than One: Phase-wise Velocity Distillation for Fast and High-Quality Image Generation
Zhen Guo, Rongyuan Wu, Qiaosi Yi +3
Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly. While diffusion distillation techniques can…
LDM-is-AE: Latent Diffusion Model is an Auto-Encoder for End-to-End Image Generation
Zhengqiang Zhang, Lingchen Sun, Rongyuan Wu +4
Latent Diffusion Models (LDMs) typically adopt a two-stage pipeline: an auto-encoder (AE) is first pre-trained to define a latent space, then a diffusion model is trained to perfor…
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…
VOSR: A Vision-Only Generative Model for Image Super-Resolution
Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang +4
Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effecti…
GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution
Qiaosi Yi, Shuai Li, Rongyuan Wu +3
Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step ge…
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…
Photo3D: Advancing Photorealistic 3D Generation through Structure-Aligned Detail Enhancement
Xinyue Liang, Zhinyuan Ma, Lingchen Sun +2
Although recent 3D-native generators have made great progress in synthesizing reliable geometry, they still fall short in achieving realistic appearances. A key obstacle lies in th…
NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution
Xiangtao Kong, Rongyuan Wu, Shuaizheng Liu +2
Most recent real-world image super-resolution (Real-ISR) methods employ pre-trained text-to-image (T2I) diffusion models to synthesize the high-quality image either from random Gau…
AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
Xinyue Liang, Zhiyuan Ma, Lingchen Sun +2
Single-image-to-3D models typically follow a sequential generation and reconstruction workflow. However, intermediate multi-view images synthesized by pre-trained generation models…
One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
Yujing Sun, Lingchen Sun, Shuaizheng Liu +3
It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pr…
InstructRestore: Region-Customized Image Restoration with Human Instructions
Shuaizheng Liu, Jianqi Ma, Lingchen Sun +2
Despite the significant progress in diffusion prior-based image restoration, most existing methods apply uniform processing to the entire image, lacking the capability to perform r…
Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models
Hongyang Wei, Shuaizheng Liu, Chun Yuan +1
By leveraging the generative priors from pre-trained text-to-image diffusion models, significant progress has been made in real-world image super-resolution (Real-ISR). However, th…