5 papers
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
Liyuan Zhu, Shengyu Huang, Amrita Mazumdar +6
We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos. Our approach conditions a video model on dense, p…
How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
Bosung Kim, Ruiyi Wang, David Acuna +5
Scaling robot policy learning is bottlenecked by the cost of collecting demonstrations, while language annotations for existing demonstrations are comparatively cheap. We study lan…
RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion
Jaidev Shriram, Alex Trevithick, Lingjie Liu +1
We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex…
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
Rundi Wu, Ruiqi Gao, Ben Poole +4
We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video. CAT4D leverages a multi-view video diffusion model trained on a diverse combination of datasets…
SimVS: Simulating World Inconsistencies for Robust View Synthesis
Alex Trevithick, Roni Paiss, Philipp Henzler +9
Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illuminat…