10 papers
A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples
Zixuan Fu, Chong Wang, Lanqing Guo +3
Pixel-space diffusion models aim to learn an end-to-end generator directly over raw pixels. This is challenging because a single model must capture both global structure and local…
HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images
Yichen Liu, Donghao Zhou, Jie Wang +9
Human-product images, which showcase the integration of humans and products, play a vital role in advertising, e-commerce, and digital marketing. The essential challenge of generat…
Improving Flexible Image Tokenizers for Autoregressive Image Generation
Zixuan Fu, Lanqing Guo, Chong Wang +3
Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, whe…
NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li, Yeying Jin, Xin Jin +134
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images. This challenge received a wide range of impressive solutions, which are devel…
Digital Staining with Knowledge Distillation: A Unified Framework for Unpaired and Paired-But-Misaligned Data
Ziwang Xu, Lanqing Guo, Satoshi Tsutsui +3
Staining is essential in cell imaging and medical diagnostics but poses significant challenges, including high cost, time consumption, labor intensity, and irreversible tissue alte…
Training-Free Text-Guided Image Editing with Visual Autoregressive Model
Yufei Wang, Lanqing Guo, Zhihao Li +4
Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows ha…