Pith. sign in

REVIEW 5 cited by

Trim 3D Gaussian Splatting for Accurate Geometry Representation

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 2406.07499 v1 pith:UQGNN22L submitted 2024-06-11 cs.CV cs.GR

Lue Fan , Yuxue Yang , Minxing Li , Hongsheng Li , Zhaoxiang Zhang This is my paper · ORCID
classification cs.CVcs.GR
keywords geometryaccurategaussiantrimgsgaussiansartsinaccurateprevious
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we introduce Trim 3D Gaussian Splatting (TrimGS) to reconstruct accurate 3D geometry from images. Previous arts for geometry reconstruction from 3D Gaussians mainly focus on exploring strong geometry regularization. Instead, from a fresh perspective, we propose to obtain accurate 3D geometry of a scene by Gaussian trimming, which selectively removes the inaccurate geometry while preserving accurate structures. To achieve this, we analyze the contributions of individual 3D Gaussians and propose a contribution-based trimming strategy to remove the redundant or inaccurate Gaussians. Furthermore, our experimental and theoretical analyses reveal that a relatively small Gaussian scale is a non-negligible factor in representing and optimizing the intricate details. Therefore the proposed TrimGS maintains relatively small Gaussian scales. In addition, TrimGS is also compatible with the effective geometry regularization strategies in previous arts. When combined with the original 3DGS and the state-of-the-art 2DGS, TrimGS consistently yields more accurate geometry and higher perceptual quality. Our project page is https://trimgs.github.io

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. Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

    cs.CL 2025-08 conditional novelty 6.0 of 10

    RayletDF predicts ray-surface distances from learned raylet segment features and shows single-forward-pass 3D surface reconstruction that generalizes across unseen indoor datasets from point clouds or pre-fit 3D Gaussians.

  2. A Mixed-Primitive-based Gaussian Splatting Method for Surface Reconstruction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MP-GS combines Gaussian ellipses, line segments, and triangles as splatting primitives and reports state-of-the-art Chamfer distance on DTU and F1 on Tanks and Temples.

  3. Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A plug-and-play 3D Chamfer loss, using pointmaps from a pretrained transformer as pseudo-ground truth, improves feed-forward 3DGS rendering and geometry across MVSplat and DepthSplat.

  4. Hybrid Mesh-Gaussian Representation for Efficient Indoor Scene Reconstruction

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A hybrid representation routes texture-rich flat indoor regions to a textured mesh and keeps Gaussians only for complex geometry, reducing Gaussian counts by 18-50% with roughly comparable rendering quality.

  5. Efficient Geometry Compression and Communication for 3D Gaussian Splatting Point Clouds

    cs.MM 2025-09 conditional novelty 3.0 of 10

    Integrating AVS PCRM geometry coding into the i3DV Gaussian platform, with Morton-code alignment, saves 10-25% total bitrate without changing rendering quality.

Pith tools