Jon Barron's point reignites debate: explicit 3D still irreplaceable
ZeeshanZiaML · x · 2026-09-01
Researchers clashed on X over whether 3D vision (3DV) still matters. Ziyang Xie cited Vincent's "bitter letter" view: explicit 3D is no longer necessary for robot learning, and video generation models are eroding its role in graphics.
But Jon Barron's counterpoint is widely seen as the key insight: for interactive media, distribution cost must be effectively zero—you cannot serve millions of users with server-side video generation, so a persistent representation (explicit scene or implicit scene latent) is still needed for real-time client-side rendering.
The original poster added a more pessimistic take: 3DV may end up confined to precision photogrammetry applications.
Related event: Jon Barron Releases CVPR Talk Questioning Explicit 3D Representations(10 posts)→
More from Multimodal
- Pollo AI launches Recast video restyling, 60% off for launch — SimplyAnnisa · 2026-10-16
- Tripo hosts first world-building hackathon in SF with World Labs and Runway talks — mhdfaran · 2026-10-16
- Kling 4.0 boosts text-to-video with character consistency and lip sync — CurieuxExplorer · 2026-10-16
- 5.8M-param Speech Event Detector adds laughs, breaths and背景 sounds to Whisper transcripts — Ayush Kumar Bar · 2026-10-16
- Huawei's SUPRA-Tex turns one image into relightable 3D materials with WYSIWYG fidelity — Chen Yang · 2026-10-16
- Giant Michael Jackson AI fashion images show the power of extreme proportions — OVolosin82152 · 2026-10-16