4 papers · 1 filter
TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing
Ruikang Li, Zixuan Chen, Jiarui Wu +6
Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into sev…
FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Ruchang Yao, Shi Guo, Junhao Zhuang +7
Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and distilled mo…
InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space
Jiarui Wu, Yujin Wang, Ruikang Li +3
Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a superior visual quality, but ofte…
PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models
Mingde Yao, Zhiyuan You, King-Man Tam +2
With the recent fast development of generative models, instruction-based image editing has shown great potential in generating high-quality images. However, the quality of editing…