Skip to main navigation Skip to search Skip to main content

LRM-Zero: Training Large Reconstruction Models with Synthesized Data

  • Desai Xie
  • , Sai Bi
  • , Zhixin Shu
  • , Kai Zhang
  • , Zexiang Xu
  • , Yi Zhou
  • , Sören Pirk
  • , Arie Kaufman
  • , Xin Sun
  • , Hao Tan
  • Adobe Systems Incorporated
  • Stony Brook University
  • Kiel University

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations

Abstract

We present LRM-Zero, a Large Reconstruction Model (LRM) trained entirely on synthesized 3D data, achieving high-quality sparse-view 3D reconstruction. The core of LRM-Zero is our procedural 3D dataset, Zeroverse, which is automatically synthesized from simple primitive shapes with random texturing and augmentations (e.g., height fields, boolean differences, and wireframes). Unlike previous 3D datasets (e.g., Objaverse) which are often captured or crafted by humans to approximate real 3D data, Zeroverse completely ignores realistic global semantics but is rich in complex geometric and texture details that are locally similar to or even more intricate than real objects. We demonstrate that our LRM-Zero, trained with our fully synthesized Zeroverse, can achieve high visual quality in the reconstruction of real-world objects, competitive with models trained on Objaverse. We also analyze several critical design choices of Zeroverse that contribute to LRM-Zero's capability and training stability. Our work demonstrates that 3D reconstruction, one of the core tasks in 3D vision, can potentially be addressed without the semantics of real-world objects. The Zeroverse's procedural synthesis code and interactive visualization are available at: https://desaixie.github.io/lrm-zero/.

Original languageEnglish
JournalAdvances in Neural Information Processing Systems
Volume37
StatePublished - 2024
Event38th Conference on Neural Information Processing Systems, NeurIPS 2024 - Vancouver, Canada
Duration: Dec 9 2024Dec 15 2024

Fingerprint

Dive into the research topics of 'LRM-Zero: Training Large Reconstruction Models with Synthesized Data'. Together they form a unique fingerprint.

Cite this