Pith. sign in

REVIEW 4 cited by

Segment Any 4D Gaussians

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 2407.04504 v2 pith:SLEDQP2F submitted 2024-07-05 cs.CV

Shengxiang Ji , Guanjun Wu , Jiemin Fang , Jiazhong Cen , Taoran Yi , Wenyu Liu , Qi Tian , Xinggang Wang This is my paper
classification cs.CV
keywords gaussianssa4dsegmentsegmentationworldabilityanythinggaussian
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Modeling, understanding, and reconstructing the real world are crucial in XR/VR. Recently, 3D Gaussian Splatting (3D-GS) methods have shown remarkable success in modeling and understanding 3D scenes. Similarly, various 4D representations have demonstrated the ability to capture the dynamics of the 4D world. However, there is a dearth of research focusing on segmentation within 4D representations. In this paper, we propose Segment Any 4D Gaussians (SA4D), one of the first frameworks to segment anything in the 4D digital world based on 4D Gaussians. In SA4D, an efficient temporal identity feature field is introduced to handle Gaussian drifting, with the potential to learn precise identity features from noisy and sparse input. Additionally, a 4D segmentation refinement process is proposed to remove artifacts. Our SA4D achieves precise, high-quality segmentation within seconds in 4D Gaussians and shows the ability to remove, recolor, compose, and render high-quality anything masks. More demos are available at: https://jsxzs.github.io/sa4d/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A self-supervised 3D Gaussian feature field, with cluster-derived segmentations, is used for accurate camera pose refinement and privacy-preserving visual localization.

  2. VolSegGS: Segmentation and Tracking in Dynamic Volumetric Scenes via Deformable 3D Gaussians

    cs.GR 2025-07 conditional novelty 6.0 of 10

    VolSegGS reconstructs dynamic volumetric scenes from rendered images with deformable 3D Gaussians and enables real-time interactive segmentation and tracking of regions over time.

  3. Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering

    cs.CV 2025-10 conditional novelty 5.0 of 10

    UGSDF achieves state-of-the-art novel-view rendering of dynamic urban objects without LiDAR or 3D motion annotations by jointly optimizing SDFs and 3D Gaussians under 2D depth and point-tracking priors.

  4. Advances in 4D Representation: Geometry, Motion, and Interaction

    cs.CV 2025-10 conditional novelty 4.0 of 10

    A representation-centric survey of 4D generation and reconstruction, organized by geometry, motion, and interaction, with qualitative trade-off comparisons across seven representation families.

Pith tools