ECCV 2026: Odoriko Enables Shape-Aware Unified Multimodal Motion Generation
mittu1204 · x · 2026-08-31
Existing unified multimodal motion frameworks ignore morphological factors like gender and body shape, treating all subjects as equivalent. Odoriko is the first unified framework (text, music, video) to incorporate bio-morphological information, generating motion consistent with "who" is moving. When explicit morphology is unavailable, it jointly recovers shape and motion. Experiments show it matches or exceeds specialized models across benchmarks while enabling morphology-consistent generation.
More from Multimodal
- Fan animation made in Blender with Claude Code (Opus 5.5) — Icy-Appointment3583 · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Tessellation-free geometric queries on displaced surfaces cut caustics variance 10x — ssh4net · 2026-10-16
- Complex multi-link CAD mechanism finally animates, dev celebrates the breakthrough — zetalyrae · 2026-10-16
- OpenMOSS releases MOSS-Image-SFT: Apache 2.0 text-to-image model on Hugging Face — bdsqlsz · 2026-10-16
- Hyperflow open-sourced: 49 sampling steps down to 8, ~3x faster video generation — mhdfaran · 2026-10-16