← Search

Dehong Kong

2 accepted papers

2026

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal

CVPR 2026

Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from substantial inference latency. For instance, although MiniMax Remover achieves state-of-the-art visual quality, it opera

Cited by 0SourcecodeScholar
2025

Dual Prompting Image Restoration with Diffusion Transformers

CVPR 2025poster

Recent state-of-the-art image restoration methods mostly adopt latent diffusion models with U-Net backbones, yet still facing challenges in achieving high-quality restoration due to their limited capabilities. Diffusion transformers (DiTs), like SD3, are emerging as a promising alternative because o…

Cited by 1SourcePDFScholar