Pith. sign in

REVIEW 5 cited by

iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matching

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 2312.09031 v2 pith:YT7IH2LO submitted 2023-12-14 cs.CV

Yuan Sun , Xuan Wang , Yunfan Zhang , Jie Zhang , Caigui Jiang , Yu Guo , Fei Wang This is my paper · ORCID
classification cs.CV
keywords poseestimationcamerainvertingaddressadversecomparinggaussian
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a method named iComMa to address the 6D camera pose estimation problem in computer vision. Conventional pose estimation methods typically rely on the target's CAD model or necessitate specific network training tailored to particular object classes. Some existing methods have achieved promising results in mesh-free object and scene pose estimation by inverting the Neural Radiance Fields (NeRF). However, they still struggle with adverse initializations such as large rotations and translations. To address this issue, we propose an efficient method for accurate camera pose estimation by inverting 3D Gaussian Splatting (3DGS). Specifically, a gradient-based differentiable framework optimizes camera pose by minimizing the residual between the query image and the rendered image, requiring no training. An end-to-end matching module is designed to enhance the model's robustness against adverse initializations, while minimizing pixel-level comparing loss aids in precise pose estimation. Experimental results on synthetic and complex real-world data demonstrate the effectiveness of the proposed approach in challenging conditions and the accuracy of camera pose estimation.

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. Camera Pose Refinement via 3D Gaussian Splatting

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    GS-SMC refines camera poses without retraining by enforcing epipolar constraints between a query photo and several photos rendered from an existing 3D Gaussian Splatting model.

  2. SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A semantic retrieval and rendering-refinement pipeline estimates camera poses from 3D Gaussian Splatting maps without an initial pose prior, reporting state-of-the-art median errors on 7Scenes and 12Scenes.

  3. A Large Catalog of DA White Dwarf Characteristics Using SDSS and Gaia Observations

    astro-ph.SR 2025-08 unverdicted novelty 5.0 of 10

    The paper publishes the largest catalog of DA white dwarf measurements to date, using SDSS DR19 plus earlier SDSS data and Gaia, and reports a systematic offset between SDSS-V and older SDSS measurements.

  4. Improving Novel view synthesis of 360$^\circ$ Scenes in Extremely Sparse Views by Jointly Training Hemisphere Sampled Synthetic Images

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A pipeline that samples and enhances synthetic upper-hemisphere views from a DUSt3R point cloud to train 3D Gaussian Splatting, improving four-view 360-degree novel view synthesis.

  5. 3DGS_LSR:Large_Scale Relocation for Autonomous Driving Based on 3D Gaussian Splatting

    cs.RO 2025-07 reject novelty 4.0 of 10

    A monocular-image relocalization pipeline using 3D Gaussian Splatting maps, SuperPoint/SuperGlue matching, and iterative PnP rendering refinement, reporting 0.026-0.081 m errors on KITTI.

Pith tools