mlsanityData to 14 Oct 2026

FroDO: From Detections to 3D Objects

arXiv 2005.05125 ↗First posted 11 May 2020cs.CVcited by 51

Not on the map. Why?

Abstract (arXiv)

Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers object location, pose and shape in a coarse-to-fine manner. Key to FroDO is to embed object shapes in a novel learnt space that allows seamless switching between sparse point cloud and dense DeepSDF decoding. Given an input sequence of localized RGB frames, FroDO first aggregates 2D detections to instantiate a category-aware 3D bounding box per object. A shape code is regressed using an encoder network before optimizing shape and pose further under the learnt shape priors using sparse and dense shape representations. The optimization uses multi-view geometric, photometric and silhouette losses. We evaluate on real-world datasets, including Pix3D, Redwood-OS, and ScanNet, for single-view, multi-view, and multi-object reconstruction.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 14; 2024: 6; 2025: 4; 2026: 2.

51 papers.

Sort:

By area:

  1. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  2. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  3. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 155
  4. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 70
  5. 2022Removing Objects From Neural Radiance Fieldscited by 66
  6. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 56
  7. 2021Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketchescited by 51
  8. 2021DSP-SLAM: Object Oriented SLAM with Deep Shape Priorscited by 30
  9. 2022In-Hand 3D Object Scanning from an RGB Sequencecited by 27
  10. 2021ODAM: Object Detection, Association, and Mapping using Posed RGB Videocited by 22
  11. 2021Pose2Room: Understanding 3D Scenes from Human Activitiescited by 22
  12. 2022Category-Aware Transformer Network for Better Human-Object Interaction Detectioncited by 22
38 more
  1. 2026ShapeR: Robust Conditional 3D Shape Generation from Casual Capturescited by 22
  2. 2021Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Imagecited by 20
  3. 2022PINs: Progressive Implicit Networks for Multi-Scale Neural Representationscited by 19
  4. 2022RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformerscited by 17
  5. 2022RangeUDF: Semantic Surface Reconstruction from 3D Point Cloudscited by 16
  6. 2023Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environmentscited by 15
  7. 2023Panoptic Mapping with Fruit Completion and Pose Estimation for Horticultural Robotscited by 14
  8. 2023CAD-Estate: Large-scale CAD Model Annotation in RGB Videoscited by 14
  9. 2023Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detectioncited by 14
  10. 2021Multi-person Implicit Reconstruction from a Single Imagecited by 13
  11. 2024AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddingscited by 13
  12. 2021ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Descriptioncited by 10
  13. 2021Learning to Better Segment Objects from Unseen Classes with Unlabeled Videoscited by 9
  14. 2022A Real World Dataset for Multi-view 3D Reconstructioncited by 9
  15. 2023Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Priorcited by 9
  16. 2023O2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Modelcited by 8
  17. 2023Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priorscited by 8
  18. 2022SDFEst: Categorical Pose and Shape Estimation of Objects from RGB-D using Signed Distance Fieldscited by 7
  19. 2021Ray-ONet: Efficient 3D Reconstruction From A Single RGB Imagecited by 6
  20. 2023Perceiving Unseen 3D Objects by Poking the Objectscited by 5
  21. 2023Virtual Occlusions Through Implicit Depthcited by 5
  22. 2024Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priorscited by 5
  23. 2023Learning-based Relational Object Matching Across Viewscited by 4
  24. 2021Dynamic Convolution for 3D Point Cloud Instance Segmentationcited by 3
  25. 2022VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstructioncited by 3
  26. 2023Structured Generative Models for Scene Understandingcited by 3
  27. 2024Free-Moving Object Reconstruction and Pose Estimation with Virtual Cameracited by 3
  28. 2024Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detectioncited by 3
  29. 2023RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluationcited by 2
  30. 2023TransPoser: Transformer as an Optimizer for Joint Object Shape and Pose Estimationcited by 2
  31. 2024CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrievalcited by 2
  32. 2021Joint stereo 3D object detection and implicit surface reconstructioncited by 1
  33. 2022Scatter Points in Space: 3D Detection from Multi-view Monocular Imagescited by 0
  34. 2023Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor Localizationcited by 0
  35. 2025Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstructioncited by 0
  36. 2025Category-level Meta-learned NeRF Priors for Efficient Object Mappingcited by 0
  37. 2025Volumetric Reconstruction From Partial Views for Task-Oriented Graspingcited by 0
  38. 2025VOCAL: Visual Odometry via ContrAstive Learningcited by 0

50 most cited of 51 All 51 (JSON)