LightGlue Team Releases FlexGlue: Pixel-Level Matching That Rejects Doppelgangers
ducha_aiki · x · 2026-11-05
The SuperGlue/LightGlue team announced FlexGlue, a new image-matching model: one model handles both sparse and dense point tracking and matching, and uniquely rejects 'doppelganger' pairs—symmetry-induced false matches that commonly break SfM. It achieves state-of-the-art SfM and matching performance at high speed, is available in COLMAP, with code and paper released.
Related event: LightGlue Team Releases FlexGlue, Topping IMC2025 Benchmarks(5 posts)→
More from Multimodal
- Voyager agent picks AI video models per shot, claims 2-3x fewer generations at half price — rohanpaul_ai · 2026-11-05
- Simulated 'ancient surveillance' videos go viral: full MiniMax H3 workflow revealed — Hailuo_AI · 2026-11-05
- Canva explores character-specific feature for CRAFT model, shows new extensions — pbaylies · 2026-11-05
- LiveFoley: real-time streaming video-to-audio generation with latency below perceptual thresholds — Yusheng Dai · 2026-11-05
- 29 speech-to-speech model launches in one year — when does s2s overtake cascades? — rdesh26 · 2026-11-05
- Krea 2 Turbo 4-step distill LoRA retrained to 133K steps with cleaner detail, less ghosting — TimeTruth2490 · 2026-11-05