Pith. sign in

REVIEW 7 cited by

3D Vision-Language Gaussian Splatting

Not yet reviewed by Pith; the record is open.

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 2410.07577 v2 pith:3VZDWKKG submitted 2024-10-10 cs.CV

classification cs.CV
keywords semanticmethodsmodalitysceneunderstandingvision-languageexistinggaussian
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality. However, current multi-modal scene understanding approaches have naively embedded semantic representations into 3D reconstruction methods without striking a balance between visual and language modalities, which leads to unsatisfying semantic rasterization of translucent or reflective objects, as well as over-fitting on color modality. To alleviate these limitations, we propose a solution that adequately handles the distinct visual and semantic modalities, i.e., a 3D vision-language Gaussian splatting model for scene understanding, to put emphasis on the representation learning of language modality. We propose a novel cross-modal rasterizer, using modality fusion along with a smoothed semantic indicator for enhancing semantic rasterization. We also employ a camera-view blending technique to improve semantic consistency between existing and synthesized views, thereby effectively mitigating over-fitting. Extensive experiments demonstrate that our method achieves state-of-the-art performance in open-vocabulary semantic segmentation, surpassing existing methods by a significant margin.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Relation-Centric Open-Vocabulary 3D Gaussian Segmentation

    cs.CV 2026-07 unverdicted novelty 7.0 of 10

    PairGS builds a relation graph from sparse pairwise affinities on 3D Gaussians to achieve SOTA open-vocabulary segmentation with a 50x faster variant than optimization-based methods.

  2. 3AM: 3egment Anything with Geometric Consistency in Videos

    cs.CV 2026-01 unverdicted novelty 7.0 of 10

    3AM integrates MUSt3R 3D features into SAM2 via a Feature Merger and FOV-aware sampling to deliver geometry-consistent video object segmentation from RGB alone, with large gains on wide-baseline datasets.

  3. GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A training-free graph-cut method selects 3D objects from Gaussian splatting scenes using sparse user scribbles, reaching 92.2 mIoU on NVOS with three interaction views.

  4. E3DGS: Unified Geometric-Photometric Equivariance for 3D Gaussian Splatting via Color-as-Geometry Embedding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    3D Gaussian view-dependent colors are repacked as 3×3 matrices so geometry and color rotate together, giving exact rotation-equivariant recognition and world modeling in 3DGS.

  5. DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    DualSplat bootstraps object-level pseudo-masks from initial 3DGS reconstruction failures using residuals and SAM2 to enable robust second-pass optimization in transient-heavy scenes.

  6. NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    NG-GS uses NeRF guidance and RBF interpolation on 3DGS to produce smoother, higher-quality object segmentation boundaries.

  7. ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting

    cs.CV 2026-07 conditional novelty 5.0 of 10

    ZeroSplat performs generalized referring segmentation in 3D Gaussian Splatting with no training or extra features, outperforming single-target baselines on two newly introduced benchmarks.

Pith tools