most citedRayZer: A Self-supervised Large View Synthesis Model

1 citations · 2 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CV20251 cited

RayZer: A Self-supervised Large View Synthesis Model

Hanwen Jiang, Hao Tan, Peng Wang +8

We present RayZer, a self-supervised multi-view 3D Vision model trained without any 3D supervision, i.e., camera poses and scene geometry, while exhibiting emerging 3D awareness. C…

cs.CV20251 cited

Reconstructing Humans with a Biomechanically Accurate Skeleton

Yan Xia, Xiaowei Zhou, Etienne Vouga +2

In this paper, we introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model. To achieve this, we train a transformer that…

cs.CV2024

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Hanwen Jiang, Zexiang Xu, Desai Xie +11

We propose scaling up 3D scene reconstruction by training with synthesized data. At the core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K scenes -…

cs.CV2024

FIction: 4D Future Interaction Prediction from Video

Kumar Ashutosh, Georgios Pavlakos, Kristen Grauman

Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames-cap…

cs.RO2024

OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation

Jinhan Li, Yifeng Zhu, Yuqi Xie +4

We study the problem of teaching humanoid robots manipulation skills by imitating from single video demonstrations. We introduce OKAMI, a method that generates a manipulation plan…