Jon Barron's CVPR 2026 Bitter Lessons talk: which research areas should (and shouldn't) use explicit 3D representations

jon_barron · x · 2026-08-31

Google researcher Jon Barron shares his talk from the CVPR 2026 "Bitter Lessons" workshop, split into parts for discussion. Part 1 opens with his dissertation results from his early years, setting up the central question: which research areas should, and probably shouldn't, rely on explicit 3D representations.

The rest of the talk dives into each area — robotics, movies, games, engineering — where the value of explicit 3D varies dramatically, a systematic take on the debate over whether 3D vision is being marginalized by scaling.

Related event: Jon Barron's CVPR talk: when explicit 3D representations are worth it(10 posts)→

Original post →

More from Research

Research channel →