FreeMatching turns an image generator into a generalizable dense correspondence matcher
kwangmoo_yi · x · 2026-10-23
FreeMatching (Liu et al.) repurposes an image generator into a dense correspondence matcher, extending matching beyond spatio-temporal priors: from short-range optical flow and stationary geometric matching to long-range, multi-rigid-motion, and even generative-scenario correspondences, with bidirectional warps. The authors say this enables applications impossible with traditional correspondence methods.
More from Multimodal
- ElevenLabs' Chimera pairs Eleven v4 voice with Seedance video to make character images speak — AIwithGhotai · 2026-10-23
- Open-Source Tennis Models Plus Claude Turn Video Into a World-Class Coach — tweetsatpreet · 2026-10-23
- Berkeley's StyleStream 2.0 cuts streaming voice conversion latency to 520ms, 2x faster — Berkeley · 2026-10-23
- AuroraTTS-100K: a sub-100K-parameter English TTS running 1120x real-time on GPU — Tall_Abrocoma_3533 · 2026-10-23
- How Claude edits videos: jacob_posel shares his skill-based workflow — jacob_posel · 2026-10-23
- PixAI open-sources Tagger 1.0, the 30,877-tag anime tagger behind Tsubaki.3's data curation — bdsqlsz · 2026-10-23