/tech

World Labs says Atlas combines image generation and 3D reconstruction · Digg

World Labs says Atlas combines image generation and 3D reconstruction

a16z says Atlas can capture a 3D representation of a room from just three photos, compared with the 100 to 300 previously needed.

World Labs introduced Atlas on September 1, saying it generates image and video frames with “pixel-perfect camera control” and reconstructs them in 3D. In a discussion shared by a16z, the company’s co-founders describe “new view prediction”: using images of a scene to predict how it would look from a different position in space and time. a16z says Atlas combines pixel generation and reconstruction, allowing it to capture a room in 3D from three photos rather than the 100 to 300 previously needed.

Combined views

514.4K

2 posts, first seen 6d ago

849 likes39 comments645 saves115 reposts

World Labs says Atlas combines image generation and 3D reconstruction

a16z says Atlas can capture a 3D representation of a room from just three photos, compared with the 100 to 300 previously needed.

World Labs introduced Atlas on September 1, saying it generates image and video frames with “pixel-perfect camera control” and reconstructs them in 3D. In a discussion shared by a16z, the company’s co-founders describe “new view prediction”: using images of a scene to predict how it would look from a different position in space and time. a16z says Atlas combines pixel generation and reconstruction, allowing it to capture a room in 3D from three photos rather than the 100 to 300 previously needed.

Posts from X

2 posts

A1
a16z@a16z 6 days ago
World Labs co-founders Fei-Fei Li, Justin Johnson, Ben Mildenhall, and a16z's Martin Casado on Atlas, a world model for spatial intelligence: LLMs are built on next token prediction. Video models are built on next frame prediction. Atlas is built on new view prediction, and…
Why World Models Could Change Robotics, 3D, and CreativityFrom youtube.com
- likes: 686
- replies: 30
- bookmarks: 578
- reposts: 102
A1
a16z@a16z 6 days ago
Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I…
- likes: 163
- replies: 9
- bookmarks: 67
- reposts: 13

Combined views

514.4K

2 posts, first seen 6d ago

849 likes39 comments645 saves115 reposts

Posts from X

2 posts

A1
a16z@a16z 6 days ago
World Labs co-founders Fei-Fei Li, Justin Johnson, Ben Mildenhall, and a16z's Martin Casado on Atlas, a world model for spatial intelligence: LLMs are built on next token prediction. Video models are built on next frame prediction. Atlas is built on new view prediction, and…
Why World Models Could Change Robotics, 3D, and CreativityFrom youtube.com
- likes: 686
- replies: 30
- bookmarks: 578
- reposts: 102
A1
a16z@a16z 6 days ago
Old footage sitting in your camera roll could now be reconstructable as a 3D scene. World Labs co-founders Ben Mildenhall and Fei-Fei Li on how Atlas got there: Ben: "In a casual sense... I took three photos of this object, or six photos of this room. I look at the photos, I…
- likes: 163
- replies: 9
- bookmarks: 67
- reposts: 13

Source Posts

@a16zWorld Labs co-founders Fei-Fei Li, Justin Johnson, Ben Mildenhall, and a16z's Martin Casado on Atlas, a world model for spatial intelligence: LLMs are built on next token prediction. Video models are built on next frame prediction. Atlas is built on new view prediction, and it's the first model to unify pixel generation and pixel reconstruction, two problems computer vision has kept in separate tracks for half a century. The practical result is a 50 to 100x reduction in what it takes to digitally capture a 3D representation of a space. Previously, you needed 100 to 300 photos of a single room. Atlas can work from just three. In this conversation, they get into the slow motion shot from The Matrix that took hundreds of cameras and now takes three iPhones, the overnight Slack message that made them bet the company in five seconds, why robotics is bottlenecked on data rather than chips, and the case that new view prediction is AI-complete. 00:00 Intro 01:50 The Matrix slow motion scene now takes three iPhones 02:48 Why new view prediction is the primitive 07:10 Unifying generation and reconstruction 11:15 Gaussian splats became the bottleneck 14:17 Dense capture used to mean 300 photos 17:30 Why reconstruction needs generation to fill the gaps 18:44 The LLM lesson image models missed 23:39 The video that made them go all in 28:04 3D design is 95% revisions 30:50 The problem in robotics is data, not chips 32:48 Why a robot policy can't be trained like an image model 34:44 When the simulator becomes the planner 36:45 Frozen time required footage full of movement 40:57 Why new view prediction is AI-complete 42:43 Nature gave animals eyes but not trees YouTube: https://www.youtube.com/watch?v=qn1QDDBnTA0 @drfeifei @jcjohnss @BenMildenhall @theworldlabs @martin_casado