mlsanityData to 14 Oct 2026

Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation

arXiv 2307.15514 ↗First posted 28 Jul 2023cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through RANSAC-based algorithms or by directly regressing the pose with end-to-end optimisations. We argue that learning point-level discriminative features is overlooked in the literature. To this end, we revisit Fully Convolutional Geometric Features (FCGF) and tailor it for object 6D pose estimation to achieve state-of-the-art performance. FCGF employs sparse convolutions and learns point-level features using a fully-convolutional network by optimising a hardest contrastive loss. We can outperform recent competitors on popular benchmarks by adopting key modifications to the loss and to the input data representations, by carefully tuning the training strategies, and by employing data augmentations suitable for the underlying problem. We carry out a thorough ablation to study the contribution of each modification. The code is available at https://github.com/jcorsetti/FCGF6D.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 28 Jul 2023.

Builds on

31 of 45 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  7. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  8. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  9. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  10. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  11. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  12. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
19 more
  1. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  2. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 190
  3. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  4. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  5. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  6. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  7. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  8. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  9. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  10. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  11. 2019Single-Stage 6D Object Pose Estimationcited by 88
  12. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  13. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  14. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 42
  15. 2021PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimationcited by 17
  16. 2019Vision-based Robotic Grasping From Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Reviewcited by 12
  17. 2022DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimationcited by 9
  18. 2021Fully Convolutional Geometric Features for Category-level Object Alignmentcited by 6
  19. 2015DeepHash: Getting Regularization, Depth and Fine-Tuning Rightcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 3.

7 papers.

  1. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 57
  2. 2024A Survey of Embodied Learning for Object-Centric Robotic Manipulationcited by 35
  3. 2023Open-vocabulary object 6D pose estimationcited by 29
  4. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  5. 2024High-resolution open-vocabulary object 6D pose estimationcited by 10
  6. 2025Fully-Geometric Cross-Attention for Point Cloud Registrationcited by 3
  7. 2025Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimationcited by 0