Pith. sign in

REVIEW 3 cited by

Efficient Density Control 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 2411.10133 v4 pith:QO7INRRX submitted 2024-11-15 cs.CV

Xiaobin Deng , Changyu Diao , Min Li , Ruohan Yu , Duanqing Xu This is my paper
classification cs.CV
keywords gaussiansperformancequalityrenderingcontroldensityefficientgaussian
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

3D Gaussian Splatting (3DGS) has demonstrated outstanding performance in novel view synthesis, achieving a balance between rendering quality and real-time performance. 3DGS employs Adaptive Density Control (ADC) to increase the number of Gaussians. However, the clone and split operations within ADC are not sufficiently efficient, impacting optimization speed and detail recovery. Additionally, overfitted Gaussians that affect rendering quality may exist, and the original ADC is unable to remove them. To address these issues, we propose two key innovations: (1) Long-Axis Split, which precisely controls the position, shape, and opacity of child Gaussians to minimize the difference before and after splitting. (2) Recovery-Aware Pruning, which leverages differences in recovery speed after resetting opacity to prune overfitted Gaussians, thereby improving generalization performance. Experimental results show that our method significantly enhances rendering quality. Due to resubmission reasons, this version has been abandoned. The improved version is available at https://xiaobin2001.github.io/improved-gs-web .

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction

    cs.CV 2026-07 accept novelty 6.0 of 10

    A geometry and gradient-based partitioning strategy enables scalable block-wise 3D Gaussian Splatting for large-scale panoramic outdoor scenes.

  2. Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Perceptual-GS guides 3D Gaussian densification with a learnable sensitivity branch trained on binary edge maps, improving LPIPS and reducing Gaussian count compared with vanilla 3DGS.

  3. Decomposing Densification in Gaussian Splatting for Faster 3D Scene Reconstruction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A split-then-clone densification schedule with energy-guided multi-resolution training roughly halves 3D Gaussian Splatting training time while keeping reconstruction quality.

Pith tools