mlsanityData to 7 Oct 2026

Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction

arXiv 1706.07036 ↗First posted 21 Jun 2017cs.CV cs.LGcited by 133

Not on the map. Why?

Abstract (arXiv)

Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones. However, these methods are computationally wasteful in attempt to predict 3D shapes, where information is rich only on the surfaces. In this paper, we propose a novel 3D generative modeling framework to efficiently generate object shapes in the form of dense point clouds. We use 2D convolutional operations to predict the 3D structure from multiple viewpoints and jointly apply geometric reasoning with 2D projection optimization. We introduce the pseudo-renderer, a differentiable module to approximate the true rendering operation, to synthesize novel depth maps for optimization. Experimental results for single-image 3D object reconstruction tasks show that we outperforms state-of-the-art methods in terms of shape similarity and prediction density.

Key facts. Cited by 133 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 40; 2022: 31; 2023: 27; 2024: 17; 2025: 11; 2026: 7.

133 papers.

Sort:

By area:

  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  3. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  4. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  5. 2021Advances in Neural Renderingcited by 365
  6. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  7. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  8. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  9. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 111
  10. 2021Stylizing 3D Scene via Implicit Representation and HyperNetworkcited by 103
  11. 2023Neural Kernel Surface Reconstructioncited by 102
  12. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
38 more
  1. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  2. 2021The Power of Points for Modeling Humans in Clothingcited by 90
  3. 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
  4. 2023AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Controlcited by 84
  5. 2021SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elementscited by 72
  6. 2022DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Imagescited by 69
  7. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  8. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  9. 2024Advances in 3D Generation: A Surveycited by 62
  10. 2021Neural Fields as Learnable Kernels for 3D Reconstructioncited by 58
  11. 2023Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collectionscited by 54
  12. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  13. 2022Learning Implicit Templates for Point-Based Clothed Human Modelingcited by 50
  14. 2022NeuPhysics: Editable Neural Geometry and Physics from Monocular Videoscited by 50
  15. 2022Vox-Surf: Voxel-based Implicit Surface Representationcited by 49
  16. 2021Point-set Distances for Learning Representations of 3D Point Cloudscited by 48
  17. 20223D Shape Reconstruction from 2D Images with Disentangled Attribute Flowcited by 45
  18. 2022Approximate Differentiable Rendering with Algebraic Surfacescited by 44
  19. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  20. 2022Text and Image Guided 3D Avatar Generation and Manipulationcited by 35
  21. 2021DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimizationcited by 33
  22. 2023NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Imagescited by 32
  23. 2023A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsamplingcited by 28
  24. 2021Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matchingcited by 26
  25. 2023CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulationcited by 26
  26. 2025DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundnesscited by 24
  27. 2023CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decompositioncited by 21
  28. 2021CoCoNets: Continuous Contrastive 3D Scene Representationscited by 19
  29. 2024GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstructioncited by 18
  30. 2022RangeUDF: Semantic Surface Reconstruction from 3D Point Cloudscited by 16
  31. 2023ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistencycited by 16
  32. 2023DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Fieldcited by 16
  33. 2021StrobeNet: Category-Level Multiview Reconstruction of Articulated Objectscited by 14
  34. 2021FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registrationcited by 14
  35. 2023Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene Stylizationcited by 14
  36. 2025TSGS: Improving Gaussian Splatting for Transparent Surface Reconstruction via Normal and De-lighting Priorscited by 14
  37. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  38. 2021Vision-based Neural Scene Representations for Spacecraftcited by 12

50 most cited of 133 All 133 (JSON)