Pith. sign in

REVIEW 5 cited by

Relaxing Accurate Initialization Constraint 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 2403.09413 v2 pith:U3ZZAWIL submitted 2024-03-14 cs.CV

Jaewoo Jung , Jisang Han , Honggyu An , Jiwon Kang , Seonghoon Park , Seungryong Kim This is my paper · ORCID
classification cs.CV
keywords cloudpointaccurateinitializationrain-gsgaussiansplattinganalysis
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

3D Gaussian splatting (3DGS) has recently demonstrated impressive capabilities in real-time novel view synthesis and 3D reconstruction. However, 3DGS heavily depends on the accurate initialization derived from Structure-from-Motion (SfM) methods. When the quality of the initial point cloud deteriorates, such as in the presence of noise or when using randomly initialized point cloud, 3DGS often undergoes large performance drops. To address this limitation, we propose a novel optimization strategy dubbed RAIN-GS (Relaing Accurate Initialization Constraint for 3D Gaussian Splatting). Our approach is based on an in-depth analysis of the original 3DGS optimization scheme and the analysis of the SfM initialization in the frequency domain. Leveraging simple modifications based on our analyses, RAIN-GS successfully trains 3D Gaussians from sub-optimal point cloud (e.g., randomly initialized point cloud), effectively relaxing the need for accurate initialization. We demonstrate the efficacy of our strategy through quantitative and qualitative comparisons on multiple datasets, where RAIN-GS trained with random point cloud achieves performance on-par with or even better than 3DGS trained with accurate SfM point cloud. Our project page and code can be found at https://ku-cvlab.github.io/RAIN-GS.

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. The Role of Initialization in 3D Gaussian Splatting

    cs.CV 2026-03 unverdicted novelty 6.0 of 10

    Dense initialization of 3DGS does not consistently beat sparse SfM initialization for standard novel views, but improves off-trajectory generalization; no densification method wins everywhere.

  2. NeRF Is a Valuable Assistant for 3D Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    NeRF-GS jointly optimizes a NeRF and a 3D Gaussian Splatting model in one scene, using shared features, residual corrections, and mutual loss constraints to beat both standalone methods.

  3. GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition

    cs.RO 2026-07 conditional novelty 5.0 of 10

    A real-time Gaussian-splatting SLAM system densifies sparse ORB-SLAM2 maps with epipolar-filtered optical flow and splits long routes into localized MLP regions, completing 4500-frame outdoor sequences the leading sys...

  4. AttentionGS: Towards Initialization-Free 3D Gaussian Splatting via Structural Attention

    cs.CV 2025-06 conditional novelty 5.0 of 10

    An empirical 3DGS variant that trains from random point initialization with edge-weighted, opacity-weighted, and channel-weighted loss terms, reporting large gains on Mip-NeRF 360 and LLFF.

  5. RobustSplat: Decoupling Densification and Dynamics for Transient-Free 3DGS

    cs.CV 2025-06 conditional novelty 5.0 of 10

    RobustSplat improves transient-free 3D Gaussian Splatting by postponing densification to 10,000 iterations and bootstrapping mask supervision from low to high resolution.

Pith tools