mlsanityData to 7 Oct 2026

Volumetric and Multi-View CNNs for Object Classification on 3D Data

arXiv 1604.03265 ↗First posted 12 Apr 2016cs.CV cs.AIcited by 240

Not on the map. Why?

Abstract (arXiv)

3D shape models are becoming widely available and easier to capture, making available 3D information crucial for progress in object classification. Current state-of-the-art methods rely on CNNs to address this problem. Recently, we witness two types of CNNs being developed: CNNs based upon volumetric representations versus CNNs based upon multi-view representations. Empirical results from these two types of CNNs exhibit a large gap, indicating that existing volumetric CNN architectures and approaches are unable to fully exploit the power of 3D representations. In this paper, we aim to improve both volumetric CNNs and multi-view CNNs according to extensive analysis of existing approaches. To this end, we introduce two distinct network architectures of volumetric CNNs. In addition, we examine multi-view CNNs, where we introduce multi-resolution filtering in 3D. Overall, we are able to outperform current state-of-the-art methods for both volumetric CNNs and multi-view CNNs. We provide extensive experiments designed to evaluate underlying design choices, thus providing a better understanding of the space of methods available for object classification on 3D data.

Key facts. Cited by 240 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 90; 2022: 52; 2023: 46; 2024: 34; 2025: 13; 2026: 5.

240 papers.

Sort:

By area:

  1. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  2. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  3. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  4. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  5. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 288
  6. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  7. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  8. 2021Group-Free 3D Object Detection via Transformerscited by 215
  9. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  10. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  11. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  12. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
38 more
  1. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  2. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  3. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  4. 2024RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPScited by 110
  5. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  6. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  7. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  8. 2022Compressible-composable NeRF via Rank-residual Decompositioncited by 92
  9. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  10. 2022Surface Representation for Point Cloudscited by 84
  11. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  12. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  13. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  14. 2022TorchSparse: Efficient Point Cloud Inference Enginecited by 72
  15. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  16. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  17. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 71
  18. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  19. 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
  20. 2023Deep Learning on Implicit Neural Representations of Shapescited by 62
  21. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  22. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  23. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  24. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  25. 2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
  26. 2021SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Networkcited by 54
  27. 20213D Siamese Voxel-to-BEV Tracker for Sparse Point Cloudscited by 54
  28. 2021A Review of Location Encoding for GeoAI: Methods and Applicationscited by 53
  29. 2021Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysiscited by 47
  30. 20213D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloudcited by 45
  31. 2021PatchFormer: An Efficient Point Transformer with Patch Attentioncited by 43
  32. 2021PVT: Point-Voxel Transformer for Point Cloud Learningcited by 42
  33. 2021Joint Learning of 3D Shape Retrieval and Deformationcited by 41
  34. 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
  35. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39
  36. 2023PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimationcited by 37
  37. 2021MVT: Multi-view Vision Transformer for 3D Object Recognitioncited by 34
  38. 2024WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collectionscited by 33

50 most cited of 240 All 240 (JSON)