Dev combines Meta's DINOv3 and SAM 3.1 to track individual instruments in video
MaziyarPanahi · x · 2026-10-06
Developer Maziyar Panahi thanks Meta for DINOv3 and SAM 3.1 and previews his next experiment: following each instrument as it moves through video. The pairing of DINOv3's general-purpose visual features with SAM 3.1's segmentation is one of the most-watched combos in the open-source vision ecosystem right now.
More from Multimodal
- Google's KeyRec Achieves Best Long-Video VLM Results With Just 10% of Visual Token Budget — google · 2026-10-06
- One Week of Prompting Opus 5.5 with Blender, ElevenLabs and REAPER Yields a TV-Quality Ad — zeeg · 2026-10-06
- Seedance 2.5 demo: a melancholic 30-second forest of walking trees — LudovicCreator · 2026-10-06
- Midjourney style code 3896456162 blends 1970s Kodak film with disco aesthetics in v8.2 — michaelrabone · 2026-10-06
- Four years ago Google's Phenaki generated multi-minute videos from changing prompts — dumierhan · 2026-10-06
- A Lyrics Video for a Song That Never Existed — Fit-Case1093 · 2026-10-06