6 papers · 1 filter
KANResDiff: Learning Local Residual Diffusion via Kolmogorov-Arnold Network for Ambiguous Medical Image Segmentation
Fanding Li, Chenglin Wang, Xiangyu Li +9
Ambiguous medical image segmentation aims to provide a series of diverse but plausible segmentation hypotheses. However, existing methods introduce stochasticity in a fixed and pre…
The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results
Xiang Chen, Hao Li, Jiangxin Dong +89
This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-wo…
Fully Kolmogorov-Arnold Deep Model in Medical Image Segmentation
Xingyu Qiu, Xinghua Ma, Dong Liang +4
Deeply stacked KANs are practically impossible due to high training difficulties and substantial memory requirements. Consequently, existing studies can only incorporate few KAN la…
Ambiguity-aware Truncated Flow Matching for Ambiguous Medical Image Segmentation
Fanding Li, Xiangyu Li, Xianghe Su +6
A simultaneous enhancement of accuracy and diversity of predictions remains a challenge in ambiguous medical image segmentation (AMIS) due to the inherent trade-offs. While truncat…
Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models
Xingyu Qiu, Mengying Yang, Xinghua Ma +6
Although EDM aims to unify the design space of diffusion models, its reliance on fixed Gaussian noise prevents it from explaining emerging flow-based methods that diffuse arbitrary…
Finding Local Diffusion Schrödinger Bridge using Kolmogorov-Arnold Network
Xingyu Qiu, Mengying Yang, Xinghua Ma +6
In image generation, Schrödinger Bridge (SB)-based methods theoretically enhance the efficiency and quality compared to the diffusion models by finding the least costly path betwee…