Jon Barron: 3D matters most when the 3D model is the deliverable, not an intermediate
jon_barron · x · 2026-08-31
In part 5 of his talk series, Google's Jon Barron argues 3D has tremendous value when making things in the physical world—engineering, manufacturing, construction—because there the 3D model is the final deliverable, not an intermediate representation. 3D vision's role is enabling us to leverage abundant 2D data. The unsplit talk is on YouTube.
Related event: Jon Barron Releases CVPR Talk Questioning Explicit 3D Representations(10 posts)→
More from Research
- A beginner-friendly introduction to causal inference kicks off, Part 1 — Nasereliver · 2026-10-16
- FBI method trains for Pass@K with one sample per update at 12.3% of the cost — EmtiyazKhan · 2026-10-16
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16
- OneWM: unified causal training shows world and action modeling improve each other — IAAI233 · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 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