mlsanityData to 7 Oct 2026

3DCoMPaT++: An improved Large-scale 3D Vision Dataset for Compositional Recognition

arXiv 2310.18511 ↗First posted 27 Oct 2023cs.CV cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

In this work, we present 3DCoMPaT++, a multimodal 2D/3D dataset with 160 million rendered views of more than 10 million stylized 3D shapes carefully annotated at the part-instance level, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks. 3DCoMPaT++ covers 41 shape categories, 275 fine-grained part categories, and 293 fine-grained material classes that can be compositionally applied to parts of 3D objects. We render a subset of one million stylized shapes from four equally spaced views as well as four randomized views, leading to a total of 160 million renderings. Parts are segmented at the instance level, with coarse-grained and fine-grained semantic levels. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. Additionally, we report the outcomes of a data challenge organized at CVPR2023, showcasing the winning method's utilization of a modified PointNet++ model trained on 6D inputs, and exploring alternative techniques for GCR enhancement. We hope our work will help ease future research on compositional 3D Vision.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 27 Oct 2023.

Builds on

28 of 42 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  10. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,354
  11. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  12. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
16 more
  1. 2020PCT: Point cloud transformercited by 730
  2. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  3. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  4. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  5. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  6. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  7. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  8. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  9. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  10. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  11. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  12. 2020Grounded Situation Recognitioncited by 77
  13. 2020OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasetscited by 73
  14. 2022Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Poolingcited by 9
  15. 2018Learning Material-Aware Local Descriptors for 3D Shapescited by 8
  16. 2023HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labelingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 9.

20 papers.

Sort:

By area:

  1. 2025PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Datacited by 15
  2. 2024Kestrel: 3D Multimodal LLM for Part-Aware Grounded Descriptioncited by 9
  3. 2024HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generationcited by 8
  4. 2024ParSEL: Parameterized Shape Editing with Languagecited by 5
  5. 2025SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materialscited by 5
  6. 2024TexPro: Text-guided PBR Texturing with Procedural Material Modelingcited by 4
  7. 20253DCoMPaT200: Language-Grounded Compositional Understanding of Parts and Materials of 3D Shapescited by 4
  8. 2024GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3Dcited by 3
  9. 2025Name That Part: 3D Part Segmentation and Namingcited by 3
  10. 2026Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulationcited by 3
  11. 2026LychSim: A Controllable and Interactive Simulation Framework for Vision Researchcited by 3
  12. 2026MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMscited by 3
8 more
  1. 2025MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Modelscited by 2
  2. 2026PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understandingcited by 1
  3. 2026Adaptive Volumetric Mechanical Property Fields Invariant to Resolutioncited by 1
  4. 2025PRISM: Probabilistic Representation for Integrated Shape Modeling and Generationcited by 0
  5. 2026OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidancecited by 0
  6. 2026FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Historiescited by 0
  7. 20263D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Modelscited by 0
  8. 2026PART: Learning 3D Part Assembly and Retrieval with Transformerscited by 0