Pith. sign in

REVIEW 5 cited by

GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2404.19702 v1 pith:2QJGFCAX submitted 2024-04-30 cs.CV

Kai Zhang , Sai Bi , Hao Tan , Yuanbo Xiangli , Nanxuan Zhao , Kalyan Sunkavalli , Zexiang Xu This is my paper · ORCID
classification cs.CV
keywords modelgs-lrmgaussianlargeimagesper-pixelposedproject
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D Gaussian primitives from 2-4 posed sparse images in 0.23 seconds on single A100 GPU. Our model features a very simple transformer-based architecture; we patchify input posed images, pass the concatenated multi-view image tokens through a sequence of transformer blocks, and decode final per-pixel Gaussian parameters directly from these tokens for differentiable rendering. In contrast to previous LRMs that can only reconstruct objects, by predicting per-pixel Gaussians, GS-LRM naturally handles scenes with large variations in scale and complexity. We show that our model can work on both object and scene captures by training it on Objaverse and RealEstate10K respectively. In both scenarios, the models outperform state-of-the-art baselines by a wide margin. We also demonstrate applications of our model in downstream 3D generation tasks. Our project webpage is available at: https://sai-bi.github.io/project/gs-lrm/ .

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. GeoWorldAD: Geometry World Action Model for Autonomous Driving

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Grounding an autonomous-driving action model in ego-aligned multi-scale 3D geometry and latent future-geometry tokens improves NAVSIM closed-loop PDMS/EPDMS over prior geometry- and world-model-based planners.

  2. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A causal transformer with 3D RoPE generates vector-quantized 3D Gaussian latent grids autoregressively, enabling unconditional synthesis, completion, and open-ended outpainting of indoor scenes.

  3. Matrix3D: Large Photogrammetry Model All-in-One

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A single multi-modal diffusion transformer trained with masked learning performs pose estimation, depth prediction, and novel view synthesis in one model, reporting SOTA pose and NVS numbers.

  4. R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections

    cs.CV 2025-05 conditional novelty 5.0 of 10

    R3GS integrates appearance-conditioned hash features, a fine-tuned human-detector visibility map, and a fixed sky sphere into 3D Gaussian Splatting to improve novel view synthesis and relocalization on Phototourism scenes.

  5. SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A two-stage Gaussian-splatting framework with supervisor feature regularization and online animation augmentation improves monocular textured 3D human reconstruction on CustomHuman and THuman3.0.

Pith tools