2 papers
cs.CV2026
MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration
Lingshun Kong, Jiawei Zhang, Zhengpeng Duan +6
All-in-one image restoration is challenging because different degradation types, such as haze, blur, noise, and low-light, impose diverse requirements on restoration strategies, ma…
cs.CV2025
Towards Robust Time-of-Flight Depth Denoising with Confidence-Aware Diffusion Model
Changyong He, Jin Zeng, Jiawei Zhang +1
Time-of-Flight (ToF) sensors efficiently capture scene depth, but the nonlinear depth construction procedure often results in extremely large noise variance or even invalid areas.…