MnYangs / AnyMatchView on GitHub
ECCV 2026 AnyMatch synthesizes large-scale multi-modal pairs (RGB-IR/Depth/Normal/Event) from single-view images with 3D consistency via depth estimation, reprojection, inpainting, and cross-modal translation. Fine-tuning LoFTR/EDM/RoMa on Any-syn achieves SOTA cross-modal matching and zero-shot generalization.
☆21Jul 28, 2026Updated 3 months ago

Alternatives and similar repositories for AnyMatch

Users that are interested in AnyMatch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?