Pith. sign in

REVIEW 2 cited by

LRM-Zero: Training Large Reconstruction Models with Synthesized Data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.09371 v2 pith:LW24NVU7 submitted 2024-06-13 cs.CV cs.LG

classification cs.CVcs.LG
keywords lrm-zeroreconstructionzeroversesynthesizeddataobjectstrainedcore
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos

    cs.GR 2025-06 conditional novelty 7.0 of 10

    A single feed-forward transformer predicts per-pixel deformable 3D Gaussians with dense scene flow from a posed monocular video, enabling real-time dynamic view synthesis and 3D tracking.

  2. HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers

    cs.GR 2025-06 conditional novelty 6.0 of 10

    A feed-forward transformer model that adds SMPL-X neural-texture pose conditioning to LVSM, enabling single-pass human novel-view and novel-pose synthesis that surpasses prior generalizable methods on four benchmarks.

Pith tools