mlsanityData to 7 Oct 2026

AutoRecon: Automated 3D Object Discovery and Reconstruction

arXiv 2305.08810 ↗First posted 15 May 2023cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

A fully automated object reconstruction pipeline is crucial for digital content creation. While the area of 3D reconstruction has witnessed profound developments, the removal of background to obtain a clean object model still relies on different forms of manual labor, such as bounding box labeling, mask annotations, and mesh manipulations. In this paper, we propose a novel framework named AutoRecon for the automated discovery and reconstruction of an object from multi-view images. We demonstrate that foreground objects can be robustly located and segmented from SfM point clouds by leveraging self-supervised 2D vision transformer features. Then, we reconstruct decomposed neural scene representations with dense supervision provided by the decomposed point clouds, resulting in accurate object reconstruction and segmentation. Experiments on the DTU, BlendedMVS and CO3D-V2 datasets demonstrate the effectiveness and robustness of AutoRecon.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 15 May 2023.

Builds on

43 of 56 references.

References · 43

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  5. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  7. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  9. 2020Object-Centric Learning with Slot Attentioncited by 865
  10. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  11. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  12. 2020Implicit Geometric Regularization for Learning Shapescited by 707
31 more
  1. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  2. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  3. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  4. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  5. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  6. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  7. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  8. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  9. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  10. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  11. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  12. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  13. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  14. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  15. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  16. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 195
  17. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  18. 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
  19. 2022Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cutcited by 166
  20. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  21. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  22. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  23. 2021Unsupervised Discovery of Object Radiance Fieldscited by 100
  24. 2022Object Scene Representation Transformercited by 90
  25. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  26. 2022Object-Compositional Neural Implicit Surfacescited by 74
  27. 2022Neural Volumetric Object Selectioncited by 61
  28. 2022AutoRF: Learning 3D Object Radiance Fields from Single View Observationscited by 59
  29. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  30. 2022LaTeRF: Label and Text Driven Object Radiance Fieldscited by 38
  31. 2022Unsupervised Discovery and Composition of Object Light Fieldscited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 1; 2025: 3; 2026: 3.

13 papers.

Sort:

  1. 2023Language Embedded 3D Gaussians for Open-Vocabulary Scene Understandingcited by 205
  2. 2023ObjectSDF++: Improved Object-Compositional Neural Implicit Surfacescited by 38
  3. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 36
  4. 2024NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentationcited by 25
  5. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  6. 2023NTO3D: Neural Target Object 3D Reconstruction with Segment Anythingcited by 14
  7. 2023DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Featurescited by 1
  8. 2026Adaptive Volumetric Mechanical Property Fields Invariant to Resolutioncited by 1
  9. 2025xMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motioncited by 0
  10. 2025PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Modelscited by 0
  11. 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decodercited by 0
  12. 2026DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Modelscited by 0
1 more
  1. 2026FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentationcited by 0