PixARMesh rebuilds a full editable 3D scene from one photo
TheZachMueller · x · 2026-07-20
A CVPR 2026 paper from UC San Diego and Lambda, PixARMesh, turns a single photo into a fully editable 3D scene.
- The scene is represented as a single token sequence and generated autoregressively.
- It avoids SDFs, occupancy fields, and multi-stage layout optimization.
- Reported scene-level F-Score on 3D-FRONT: 33.55% vs 25.00% for DepR.
- Chamfer Distance improves from 0.153 to 0.099.
- Each object is produced as an artist-ready mesh with a few thousand faces.
The method uses pixel-aligned image features plus global scene context, then predicts object poses and meshes token by token in one forward pass. The post frames it as useful for robotics, self-driving scene reconstruction, game dev, and interior design.
More from Multimodal
- 10 practical ways to run Astra computer use on Premiere Pro for video editing — beechinour · 2026-10-27
- Krea ships Premiere Pro plugin to generate video and SFX inside the timeline — lmoroney · 2026-10-27
- Wan2GP lands on Pinokio: 1-click AI video on 6GB GPUs — cocktailpeanut · 2026-10-27
- WanGP v18.81 adds Tencent's Hy-Nomas world model, playable on 8GB VRAM — cocktailpeanut · 2026-10-27
- Butter.video wins over skeptical creator with hundreds of tasteful timeline 'blocks' for video effects — beechinour · 2026-10-27
- AI Video Pits Brock Lesnar Against Duncan the Tall in a Toy Showdown — KloneStudios · 2026-10-27