mlsanityData to 7 Oct 2026

Representation-Agnostic Shape Fields

arXiv 2203.10259 ↗First posted 19 Mar 2022cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

3D shape analysis has been widely explored in the era of deep learning. Numerous models have been developed for various 3D data representation formats, e.g., MeshCNN for meshes, PointNet for point clouds and VoxNet for voxels. In this study, we present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning. RASF is implemented with a learnable 3D grid with multiple channels to store local geometry. Based on RASF, shape embeddings for various 3D shape representations (point clouds, meshes and voxels) are retrieved by coordinate indexing. While there are multiple ways to optimize the learnable parameters of RASF, we provide two effective schemes among all in this paper for RASF pre-training: shape reconstruction and normal estimation. Once trained, RASF becomes a plug-and-play performance booster with negligible cost. Extensive experiments on diverse 3D representation formats, networks and applications, validate the universal effectiveness of the proposed RASF. Code and pre-trained models are publicly available https://github.com/seanywang0408/RASF

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 35 of its 68 references that are in the map. First posted on arXiv 19 Mar 2022.

Builds on

35 of 68 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2017Billion-scale similarity search with GPUscited by 2,477
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  10. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  11. 2015Spatial Transformer Networkscited by 1,423
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
23 more
  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  2. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  3. 2020PCT: Point cloud transformercited by 730
  4. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  5. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  6. 2017Neural 3D Mesh Renderercited by 437
  7. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  8. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  9. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  10. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  11. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  12. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 118
  13. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  14. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  15. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  16. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  17. 2019KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objectscited by 75
  18. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  19. 2020Deep Geometric Texture Synthesiscited by 51
  20. 2019Predicting Animation Skeletons for 3D Articulated Models via Volumetric Netscited by 39
  21. 2021RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scanscited by 21
  22. 2019LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networkscited by 14
  23. 2021HodgeNet: Learning Spectral Geometry on Triangle Meshescited by 13

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1.

4 papers.

  1. 2022Boosting Point Clouds Rendering via Radiance Mappingcited by 11
  2. 2022What Makes for Automatic Reconstruction of Pulmonary Segmentscited by 7
  3. 2022Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysiscited by 5
  4. 2023AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audiocited by 0