Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
Not on the map. Why?
Abstract (arXiv)
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database. The benchmark consists of two tasks: part-level segmentation of 3D shapes and 3D reconstruction from single view images. Ten teams have participated in the challenge and the best performing teams have outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures have been proposed on various 3D representations on both tasks. We report the techniques used by each team and the corresponding performances. In addition, we summarize the major discoveries from the reported results and possible trends for the future work in the field.
Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Oct 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 4; 2023: 1; 2024: 1; 2025: 1; 2026: 2.
15 papers.
Sort:
- 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variationscited by 58
- 2021BuildingNet: Learning to Label 3D Buildingscited by 33
- 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Visioncited by 31
- 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samplescited by 12
- 2021VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifoldscited by 11
- 2021Self-supervised Point Cloud Representation Learning via Separating Mixed Shapescited by 8
- 2022Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matchingcited by 8
- 2022Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learningcited by 6
- 2022PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Treescited by 1
- 2025Foundry: Distilling 3D Foundation Models for the Edgecited by 1
- 2026DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samplescited by 1
- 2021RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNscited by 0
3 more
- 2021Localized Shape Modelling with Global Coherence: An Inverse Spectral Approachcited by 0
- 2024Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attentioncited by 0
- 2026VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignmentcited by 0
- 2026VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment3 Jun 2026
- 2026DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples11 Feb 2026
- 2025Foundry: Distilling 3D Foundation Models for the Edge25 Nov 2025
- 2024Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention1 Dec 2024
- 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision30 Aug 2023
- 2022Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning19 Dec 2022
- 2022Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching26 Nov 2022
- 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples31 Oct 2022
- 2022PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees11 Aug 2022
- 2021BuildingNet: Learning to Label 3D Buildings11 Oct 2021
- 2021Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes1 Sep 2021
- 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations30 Aug 2021
- 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variationscited by 58
- 2021BuildingNet: Learning to Label 3D Buildingscited by 33
- 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Visioncited by 31
- 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samplescited by 12
- 2021VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifoldscited by 11
- 2021Self-supervised Point Cloud Representation Learning via Separating Mixed Shapescited by 8
- 2022Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matchingcited by 8
- 2022Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learningcited by 6
- 2022PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Treescited by 1
- 2025Foundry: Distilling 3D Foundation Models for the Edgecited by 1
- 2026DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samplescited by 1
- 2021RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNscited by 0
12 most cited of 15 All 15 (JSON)
- 2026VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment3 Jun 2026
- 2026DMP-3DAD: Cross-Category 3D Anomaly Detection via Realistic Depth Map Projection with Few Normal Samples11 Feb 2026
- 2025Foundry: Distilling 3D Foundation Models for the Edge25 Nov 2025
- 2024Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention1 Dec 2024
- 2023MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision30 Aug 2023
- 2022Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning19 Dec 2022
- 2022Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching26 Nov 2022
- 2022Teacher-Student Network for 3D Point Cloud Anomaly Detection with Few Normal Samples31 Oct 2022
- 2022PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees11 Aug 2022
- 2021BuildingNet: Learning to Label 3D Buildings11 Oct 2021
- 2021Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes1 Sep 2021
- 20213DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations30 Aug 2021
12 newest of 15 All 15 (JSON)