arXiv · 3D Reconstruction
Déjà View
Multi-view 3D reconstruction method that recurrently applies a single looped Transformer block to per-view features for K refinement steps, matching or beating much larger feed-forward baselines across five reconstruction benchmarks at a fraction of parameters and compute.
Open the source ↗Similar 3D & Spatial releases
- Mundo: Customized World Model
Mundo project team · Customised world model · Week 45, 2026
- Idol
Speridlabs (Alejandro Cañada, Chema Garabito) · Image-to-3D splats · Week 45, 2026
- JST-2
Viggle AI · World Model · Week 44, 2026
- PURE
Peking University, HKUST, Pengcheng Laboratory · 3D Reconstruction · Week 44, 2026
- Motion2MixamoRig
MaxLiu22 · Video Motion Retargeting · Week 43, 2026
- InfiniSplat v2
Zhejiang University, Shenzhen University, Hello TransTech and Causa Robotics · Feed-Forward Gaussian Splatting · Week 43, 2026
More from arXiv
- WavTTS
arXiv · Text-to-Speech · Week 23, 2026
- Stable-Layers
arXiv · Image Editing · Week 23, 2026
- PIXLRelight
arXiv · Image Editing · Week 22, 2026
- SEGA
arXiv · Text-to-Image · Week 22, 2026
- SCOPE
arXiv · Video Understanding · Week 22, 2026
- InstructAV2AV
arXiv · Video Editing · Week 22, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.