
Sign up to save your podcasts
Or


Vincent Sitzmann (Google Scholar) (Website) is a postdoc at MIT. His work is on neural scene representations in computer vision. Ultimately, he wants to make representations that AI agents can use to solve the same visual tasks humans solve regularly, but that are currently impossible for AI.
**Highlights from our conversation:**
👁 “Vision is about the question of building representations”
🧠 “We (humans) likely have a 3D inductive bias”
🤖 “All computer vision should be 3D computer vision. Our world is a 3d world.”
By Kanjun Qiu4.8
1616 ratings
Vincent Sitzmann (Google Scholar) (Website) is a postdoc at MIT. His work is on neural scene representations in computer vision. Ultimately, he wants to make representations that AI agents can use to solve the same visual tasks humans solve regularly, but that are currently impossible for AI.
**Highlights from our conversation:**
👁 “Vision is about the question of building representations”
🧠 “We (humans) likely have a 3D inductive bias”
🤖 “All computer vision should be 3D computer vision. Our world is a 3d world.”

26,353 Listeners

2,453 Listeners

479 Listeners

1,091 Listeners

624 Listeners

4,165 Listeners

95 Listeners

10,018 Listeners

95 Listeners

516 Listeners

73 Listeners

130 Listeners

92 Listeners

632 Listeners

472 Listeners