Jake Austin — accepted AI-conference papers

2025

Shape of Motion: 4D Reconstruction from a Single Video

Qianqian Wang, Vickie Ye, Hang Gao, Weijia Zeng, Jake Austin, Zhengqi Li +1

ICCV 2025poster

Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D motion explicitly. We introduce a method for reconstructing gener…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives

Tom Monnier, Jake Austin, Angjoo Kanazawa, Alexei A Efros, Mathieu Aubry

NeurIPS 2023poster

Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made…

Cited by 18 Source ↗PDF ↗Scholar ↗