Lune

CVPR2025Top-tier venue

Mitigating Ambiguities in 3D Classification with Gaussian Splatting

Ruiqi Zhang, Hao Zhu, Jingyi Zhao, Qi Zhang, Xun Cao, Zhan Ma

Abstract

3D classification with point cloud input is a fundamental problem in 3D vision. However, due to the discrete nature and the insufficient material description of point cloud representations, there are ambiguities in distinguishing wirelike and flat surfaces, as well as transparent or reflective objects. To address these issues, we propose Gaussian Splatting (GS) point cloud-based 3D classification. We find that the scale and rotation coefficients in the GS point cloud help characterize surface types. Specifically, wire-like surfaces consist of multiple slender Gaussian ellipsoids, while flat surfaces are composed of a few flat Gaussian ellipsoids. Additionally, the opacity in the GS point cloud represents the transparency characteristics of objects. As a result, ambiguities in point cloud-based 3D classification can be mitigated utilizing GS point cloud as input. To verify the effectiveness of GS point cloud input, we construct the first real-world GS point cloud dataset in the community, which includes 20 categories with 200 objects in each category. Experiments not only validate the superiority of GS point cloud input, especially in distinguishing ambiguous objects, but also demonstrate the generalization ability across different classification methods. Our project page: https://ruiqi-nju.github.io/MACGS .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies cites KPConv: Flexible and Deformable Convolution for Point Clouds
  • 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites PlenOctrees for Real-time Rendering of Neural Radiance Fields
  • 3D Gaussian Splatting for Real-Time Radiance Field Rendering cites Instant neural graphics primitives with a multiresolution hash encoding
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on17

  1. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  2. Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
  3. KPConv: Flexible and Deformable Convolution for Point CloudsHugues Thomas, Charles R. Qi, Jean-Emmanuel Deschaud, Beatriz Marcotegui et al.ICCV 2019 · 3,193 citations
  4. PlenOctrees for Real-time Rendering of Neural Radiance FieldsAlex Yu, Ruilong Li, Matthew Tancik, Hao Li et al.ICCV 2021 · 1,284 citations
  5. PointNeXt: Revisiting PointNet++ with Improved Training and Scaling StrategiesGuocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai et al.NeurIPS 2022 · 1,270 citations

Related papers

  1. 3DAffordSplat: Efficient Affordance Reasoning with 3D GaussiansZeming Wei, Junyi Lin, Yang Liu, Weixing Chen et al.ACM MM 2025 · 4 citations
  2. OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary UnderstandingYanmin Wu, Jiarui Meng, Haijie Li, Chenming Wu et al.NeurIPS 2024 · 191 citations
  3. SceneSplat: Gaussian Splatting-Based Scene Understanding with Vision-Language PretrainingYue Li, Qi Ma, Runyi Yang, Huapeng Li et al.ICCV 2025 · 5 citations
  4. COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian SplittingJiaxin Zhang, Junjun Jiang, Youyu Chen, Kui Jiang et al.CVPR 2025
  5. TSPE-GS: Probabilistic Depth Extraction for Semi-Transparent Surface Reconstruction via 3D Gaussian SplattingZhiyuan Xu, Nan Min, Yuhang Guo, Tong WeiAAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines