4 papers · 1 filter
Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
Xingyu Liu, Zewei He, Yu Chen +4
When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images.…
Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration
Luwei Tu, Jiawei Wu, Xing Luo +1
All-in-One Image Restoration (AiOIR) faces the fundamental challenge in reconciling conflicting optimization objectives across heterogeneous degradations. Existing methods are ofte…
MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion
Yikun Ma, Yiqing Li, Jiawei Wu +2
Generative models have made remarkable advancements and are capable of producing high-quality content. However, performing controllable editing with generative models remains chall…
BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models
Rizhao Cai, Zirui Song, Dayan Guan +4
Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles. However, their robustness against diverse s…