mlsanityData to 7 Oct 2026

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

arXiv 1604.00449 ↗First posted 2 Apr 2016cs.CV cs.AIcited by 587

Not on the map. Why?

Cited by 42 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2). The network learns a mapping from images of objects to their underlying 3D shapes from a large collection of synthetic data. Our network takes in one or more images of an object instance from arbitrary viewpoints and outputs a reconstruction of the object in the form of a 3D occupancy grid. Unlike most of the previous works, our network does not require any image annotations or object class labels for training or testing. Our extensive experimental analysis shows that our reconstruction framework i) outperforms the state-of-the-art methods for single view reconstruction, and ii) enables the 3D reconstruction of objects in situations when traditional SFM/SLAM methods fail (because of lack of texture and/or wide baseline).

Key facts. Cited by 587 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 138; 2022: 136; 2023: 144; 2024: 75; 2025: 60; 2026: 34.

587 papers.

Sort:

By area:

  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  2. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  5. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  6. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  7. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  8. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  9. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  10. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  11. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  12. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
38 more
  1. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  2. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  3. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  4. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  5. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  6. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  7. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  8. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  9. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  10. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  11. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  12. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  13. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  14. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  15. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 254
  16. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  17. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  18. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  19. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  20. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  21. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  22. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  23. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 183
  24. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  25. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 159
  26. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 159
  27. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  28. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  29. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  30. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 136
  31. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  32. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 117
  33. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  34. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  35. 2023Neural Kernel Surface Reconstructioncited by 102
  36. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  37. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  38. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94

50 most cited of 587 All 587 (JSON)