mlsanityData to 7 Oct 2026

SDFEst: Categorical Pose and Shape Estimation of Objects from RGB-D using Signed Distance Fields

arXiv 2207.04880 ↗First posted 11 Jul 2022cs.CV cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

Rich geometric understanding of the world is an important component of many robotic applications such as planning and manipulation. In this paper, we present a modular pipeline for pose and shape estimation of objects from RGB-D images given their category. The core of our method is a generative shape model, which we integrate with a novel initialization network and a differentiable renderer to enable 6D pose and shape estimation from a single or multiple views. We investigate the use of discretized signed distance fields as an efficient shape representation for fast analysis-by-synthesis optimization. Our modular framework enables multi-view optimization and extensibility. We demonstrate the benefits of our approach over state-of-the-art methods in several experiments on both synthetic and real data. We open-source our approach at https://github.com/roym899/sdfest.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 37 of its 44 references that are in the map. First posted on arXiv 11 Jul 2022.

Builds on

37 of 44 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2017Mask R-CNNcited by 7,259
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  11. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  12. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
25 more
  1. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  2. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  3. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  4. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  5. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  6. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  7. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  8. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  9. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  10. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  11. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  12. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  13. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  14. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  15. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  16. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  17. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 69
  18. 2016A Large Dataset of Object Scanscited by 64
  19. 2020NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstructioncited by 61
  20. 2020FroDO: From Detections to 3D Objectscited by 51
  21. 2020From Points to Multi-Object 3D Reconstructioncited by 29
  22. 2021iCaps: Iterative Category-level Object Pose and Shape Estimationcited by 23
  23. 2017Rethinking Reprojection: Closing the Loop for Pose-aware ShapeReconstruction from a Single Imagecited by 20
  24. 2020MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videoscited by 18
  25. 2022On the Evaluation of RGB-D-based Categorical Pose and Shape Estimationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 2; 2025: 0; 2026: 1.

7 papers.

  1. 2023SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variationscited by 12
  2. 2024OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimationcited by 10
  3. 2023Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Priorcited by 9
  4. 2023RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluationcited by 2
  5. 2023TransPoser: Transformer as an Optimizer for Joint Object Shape and Pose Estimationcited by 2
  6. 2024ShapeICP: Iterative Category-level Object Pose and Shape Estimation from Depthcited by 1
  7. 2026Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimationcited by 0