← Search

Saijie Hou

1 accepted papers

2025

OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning

ICCV 2025poster

Image Difference Captioning (IDC) aims to generate natural language descriptions of subtle differences between image pairs, requiring both precise visual change localization and coherent semantic expression. Despite recent advancements, existing datasets often lack breadth and depth, limiting their…

Cited by 0SourcePDFScholar