Pith. sign in

REVIEW 7 cited by

ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining

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 2408.10906 v2 pith:OFYJAR3Z submitted 2024-08-20 cs.CV

Qi Ma , Yue Li , Bin Ren , Nicu Sebe , Ender Konukoglu , Theo Gevers , Luc Van Gool , Danda Pani Paudel This is my paper · ORCID
classification cs.CV
keywords datasetgaussiantasksrepresentationshapesplatcentroidsclassificationdatasets
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks. This calls for the 3D understanding directly in this representation space. To facilitate the research in this direction, we first build ShapeSplat, a large-scale dataset of 3DGS using the commonly used ShapeNet, ModelNet and Objaverse datasets. Our dataset ShapeSplat consists of 206K objects spanning over 87 unique categories, whose labels are in accordance with the respective datasets. The creation of this dataset utilized the compute equivalent of 3.8 GPU years on a TITAN XP GPU. We utilize our dataset for unsupervised pretraining and supervised finetuning for classification and segmentation tasks. To this end, we introduce Gaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters. Through exhaustive experiments, we provide several valuable insights. In particular, we show that (1) the distribution of the optimized GS centroids significantly differs from the uniformly sampled point cloud (used for initialization) counterpart; (2) this change in distribution results in degradation in classification but improvement in segmentation tasks when using only the centroids; (3) to leverage additional Gaussian parameters, we propose Gaussian feature grouping in a normalized feature space, along with splats pooling layer, offering a tailored solution to effectively group and embed similar Gaussians, which leads to notable improvement in finetuning tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. 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.

  2. Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Can3Tok tokenizes scene-level 3D Gaussian splats into canonical latent tokens with normalization and saliency filtering, enabling reconstruction and text/image-to-3D generation.

  3. Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor

    cs.GR 2025-06 conditional novelty 6.0 of 10

    Two small mapping networks connect a frozen 3D encoder to a frozen 3D generator, so the generator decompresses objects from latent codes as small as 3 KB, achieving up to 2187x compression on meshes.

  4. You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

    cs.CV 2024-12 reject novelty 6.0 of 10

    See3D proposes a pose-free visual condition for multi-view diffusion trained on web videos, claiming SOTA single- and sparse-view 3D generation, but the evaluation protocol leaks ground-truth information and mixes ben...

  5. RoboPearls: Editable Video Simulation for Robot Manipulation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    RoboPearls is a 3D Gaussian Splatting based framework that edits demonstration videos into varied photorealistic simulations, and training on them improves robot manipulation success rates on RLBench and COLOSSEUM.

  6. Ultra Ethernet's Design Principles and Architectural Innovations

    cs.NI 2025-08 unverdicted novelty 3.0 of 10

    The abstract describes Ultra Ethernet 1.0 as a transformative networking standard whose Ultra Ethernet Transport aims for fully hardware-accelerated reliable communication; the accompanying full text is a different paper.

  7. A Survey on 3D Reconstruction Techniques in Plant Phenotyping: From Classical Methods to Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and Beyond

    eess.IV 2025-04 conditional novelty 1.0 of 10

    A review of 3D reconstruction techniques for plant phenotyping, comparing classical methods, NeRF, and 3D Gaussian Splatting on methodology, applications, and future directions.

Pith tools