activity
20242026
collaborators

7 papers

cs.CV2026

Backbone-Agnostic Stochastic Perturbation Learning for End-to-End Real-World Image Dehazing

Bingcai Wei, Yuning Cui, Mingyu Liu +5

Real-world paired image dehazing remains challenging because haze degradation is spatially non-uniform, illumination-dependent, and physically ambiguous even when haze-free referen…

cs.CV2026

CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs

Xingcheng Zhou, Hao Guo, Rui Song +5

Safety-critical traffic reasoning requires contrastive consistency: models must detect true hazards when an accident occurs, and reliably reject plausible-but-false hypotheses unde…

cs.CV2026

LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

Xiang Chen, Hao Li, Jiangxin Dong +54

This paper presents a review for the LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aimed to advance research on real-world all-in-one image restoration…

cs.CV2026

SGTA: Scene-Graph Based Multi-Modal Traffic Agent for Video Understanding

Xingcheng Zhou, Mingyu Liu, Walter Zimmer +2

We present Scene-Graph Based Multi-Modal Traffic Agent (SGTA), a modular framework for traffic video understanding that combines structured scene graphs with multi-modal reasoning.…

cs.CV2025

CAS-IQA: Teaching Vision-Language Models for Synthetic Angiography Quality Assessment

Bo Wang, De-Xing Huang, Xiao-Hu Zhou +5

Synthetic X-ray angiographies generated by modern generative models hold great potential to reduce the use of contrast agents in vascular interventional procedures. However, low-qu…

cs.CV2025

TUMTraffic-VideoQA: A Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes

Xingcheng Zhou, Konstantinos Larintzakis, Hao Guo +7

We present TUMTraffic-VideoQA, a novel dataset and benchmark designed for spatio-temporal video understanding in complex roadside traffic scenarios. The dataset comprises 1,000 vid…