mlsanityData to 14 Oct 2026

Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features

arXiv 2209.05624 ↗First posted 12 Sep 2022cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

We consider the problem of category-level 6D pose estimation from a single RGB image. Our approach represents an object category as a cuboid mesh and learns a generative model of the neural feature activations at each mesh vertex to perform pose estimation through differentiable rendering. A common problem of rendering-based approaches is that they rely on bounding box proposals, which do not convey information about the 3D rotation of the object and are not reliable when objects are partially occluded. Instead, we introduce a coarse-to-fine optimization strategy that utilizes the rendering process to estimate a sparse set of 6D object proposals, which are subsequently refined with gradient-based optimization. The key to enabling the convergence of our approach is a neural feature representation that is trained to be scale- and rotation-invariant using contrastive learning. Our experiments demonstrate an enhanced category-level 6D pose estimation performance compared to prior work, particularly under strong partial occlusion.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

23 of 42 references.

References · 23

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2013Describing Textures in the Wildcited by 2,125
  4. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  6. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  7. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  8. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  9. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  10. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  11. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  12. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
11 more
  1. 20176-DoF Object Pose from Semantic Keypointscited by 89
  2. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  3. 2020Robust Object Detection under Occlusion with Context-Aware CompositionalNetscited by 54
  4. 2020Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusioncited by 47
  5. 2018StarMap for Category-Agnostic Keypoint and Viewpoint Estimationcited by 42
  6. 2021NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimationcited by 41
  7. 2020Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusioncited by 38
  8. 2019Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusioncited by 24
  9. 2020Robust Instance Segmentation through Reasoning about Multi-Object Occlusioncited by 23
  10. 2021Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Posecited by 15
  11. 2020CoKe: Localized Contrastive Learning for Robust Keypoint Detectioncited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 9; 2025: 4; 2026: 2.

23 papers.

Sort:

By area:

  1. 2024pix2gestalt: Amodal Segmentation by Synthesizing Wholescited by 70
  2. 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoningcited by 68
  3. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  4. 2025SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Modelscited by 38
  5. 2024ImageNet3D: Towards General-Purpose Object-Level 3D Understandingcited by 25
  6. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  7. 2023Generating Images with 3D Annotations Using Diffusion Modelscited by 18
  8. 2024Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answeringcited by 18
  9. 20233D-Aware Visual Question Answering about Parts, Poses and Occlusionscited by 16
  10. 2023OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Imagescited by 12
  11. 2023Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentationcited by 11
  12. 2024iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learningcited by 10
11 more
  1. 2024Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimationcited by 7
  2. 2024Reconstructing Animals and the Wildcited by 7
  3. 2022Video based Object 6D Pose Estimation using Transformerscited by 5
  4. 2023Neural Textured Deformable Meshes for Robust Analysis-by-Synthesiscited by 4
  5. 2025Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypescited by 4
  6. 2024WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusioncited by 3
  7. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  8. 2024Learning a Category-level Object Pose Estimator without Pose Annotationscited by 1
  9. 2025DINeMo: Learning Neural Mesh Models with no 3D Annotationscited by 0
  10. 2026PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Viewscited by 0
  11. 2026Emergence of a Shared Canonical Object Frame from In-the-Wild Videoscited by 0