Pith. sign in

REVIEW 10 cited by

Occam's LGS: An Efficient Approach for Language 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 2412.01807 v2 pith:MS5QYAMX submitted 2024-12-02 cs.CV

Jiahuan Cheng , Jan-Nico Zaech , Luc Van Gool , Danda Pani Paudel This is my paper
classification cs.CV
keywords gaussiansplattinglanguageefficientapproachfeaturesoccamrepresentation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

TL;DR: Gaussian Splatting is a widely adopted approach for 3D scene representation, offering efficient, high-quality reconstruction and rendering. A key reason for its success is the simplicity of representing scenes with sets of Gaussians, making it interpretable and adaptable. To enhance understanding beyond visual representation, recent approaches extend Gaussian Splatting with semantic vision-language features, enabling open-set tasks. Typically, these language features are aggregated from multiple 2D views, however, existing methods rely on cumbersome techniques, resulting in high computational costs and longer training times. In this work, we show that the complicated pipelines for language 3D Gaussian Splatting are simply unnecessary. Instead, we follow a probabilistic formulation of Language Gaussian Splatting and apply Occam's razor to the task at hand, leading to a highly efficient weighted multi-view feature aggregation technique. Doing so offers us state-of-the-art results with a speed-up of two orders of magnitude without any compression, allowing for easy scene manipulation. Project Page: https://insait-institute.github.io/OccamLGS/

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 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. OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    OP2GS adds instance identities and dual opacities to 3D Gaussians so that visual rendering and object-mask rendering are handled by separate opacity channels, reducing label contamination while attaching semantics at ...

  3. OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    OpenGaFF combines a geometry-conditioned Gaussian Feature Field with codebook-guided attention to deliver more spatially coherent open-vocabulary 3D semantic segmentation than prior methods.

  4. NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    A variance-aware conditional MLP operating on 3D Gaussians corrects semantic errors from multi-view inconsistent 2D features to produce more accurate and robust 3D semantic Gaussian Splatting.

  5. Visually-grounded Humanoid Agents

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    A coupled world-agent framework uses 3D Gaussian reconstruction and first-person RGB-D perception with iterative planning to enable goal-directed, collision-avoiding humanoid behavior in novel reconstructed scenes.

  6. C3G: Learning Compact 3D Representations with 2K Gaussians

    cs.CV 2025-12 unverdicted novelty 6.0 of 10

    C3G creates compact 3D Gaussian representations with 2K points by guiding placement via learnable tokens that aggregate multi-view features through attention, yielding better efficiency and performance than dense methods.

  7. CF3: Compact and Fast 3D Feature Fields

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CF3 builds a compact 3D feature field from a pre-trained 3DGS by feature lifting, per-Gaussian autoencoding, and adaptive sparsification, matching baseline segmentation quality with roughly 5% of the Gaussians.

  8. OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    OpenGaFF introduces a Gaussian Feature Field with codebook attention for open-vocabulary 3D semantic understanding, claiming better segmentation and 3D consistency than prior methods on benchmarks.

  9. OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    OpenGaFF adds a geometry-conditioned Gaussian Feature Field and codebook-guided attention to 3D Gaussian Splatting for spatially consistent open-vocabulary 3D semantic understanding.

  10. Disentangling concept semantics via multilingual averaging in Sparse Autoencoders

    cs.CL 2025-08 unverdicted novelty 4.0 of 10

    The abstract claims multilingual averaging of Gemma Scope activations aligns with ontology ground truth better than any single language, but the provided full text is an unrelated paper and contains no supporting evidence.

Pith tools