GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizations
Not on the map. Why?
Abstract (arXiv)
We present GenAnalysis, an implicit shape generation framework that allows joint analysis of man-made shapes, including shape matching and joint shape segmentation. The key idea is to enforce an as-affine-as-possible (AAAP) deformation between synthetic shapes of the implicit generator that are close to each other in the latent space, which we achieve by designing a regularization loss. It allows us to understand the shape variation of each shape in the context of neighboring shapes and also offers structure-preserving interpolations between the input shapes. We show how to extract these shape variations by recovering piecewise affine vector fields in the tangent space of each shape. These vector fields provide single-shape segmentation cues. We then derive shape correspondences by iteratively propagating AAAP deformations across a sequence of intermediate shapes. These correspondences are then used to aggregate single-shape segmentation cues into consistent segmentations. We conduct experiments on the ShapeNet dataset to show superior performance in shape matching and joint shape segmentation over previous methods.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 50 of its 110 references that are in the map. First posted on arXiv 2 Mar 2025.
Builds on
50 of 110 references.
References · 50
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2023Segment Anythingcited by 8,234
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
- 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
- 2020Implicit Geometric Regularization for Learning Shapescited by 710
38 more
- 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
- 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
- 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
- 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 259
- 2019Learning Shape Templates with Structured Implicit Functionscited by 242
- 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
- 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
- 2019CvxNet: Learnable Convex Decompositioncited by 174
- 2023SAM3D: Segment Anything in 3D Scenescited by 157
- 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 124
- 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
- 20183D Point Capsule Networkscited by 106
- 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
- 2019Learning elementary structures for 3D shape generation and matchingcited by 98
- 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
- 2019Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generationcited by 90
- 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
- 2020Deep Implicit Templates for 3D Shape Representationcited by 86
- 2022Learning Smooth Neural Functions via Lipschitz Regularizationcited by 86
- 2021NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Gocited by 81
- 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
- 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
- 2020KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotationscited by 51
- 2017Deformable Shape Completion with Graph Convolutional Autoencoderscited by 50
- 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
- 2021ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generatorscited by 40
- 2023Test-Time Training on Video Streamscited by 37
- 20223D Highlighter: Localizing Regions on 3D Shapes via Text Descriptionscited by 32
- 2021Augmenting Implicit Neural Shape Representations with Explicit Deformation Fieldscited by 19
- 2022Elastic shape analysis of surfaces with second-order Sobolev metrics: a comprehensive numerical frameworkcited by 19
- 2018Parsing Geometry Using Structure-Aware Shape Templatescited by 16
- 2021GLASS: Geometric Latent Augmentation for Shape Spacescited by 16
- 2024iSeg: Interactive 3D Segmentation via Interactive Attentioncited by 14
- 2023GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Modelscited by 11
- 2019Variational Auto-Decoder: A Method for Neural Generative Modeling from Incomplete Datacited by 10
- 2023DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objectscited by 10
- 2015Data-Driven Shape Analysis and Processingcited by 8
- 2023DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentationcited by 7
Built on by
Citing papers per year: 2026: 3.
3 papers.