mlsanityData to 7 Oct 2026

CNOS: A Strong Baseline for CAD-based Novel Object Segmentation

arXiv 2307.11067 ↗First posted 20 Jul 2023cs.CVcited by 86

Not on the map. Why?

Abstract (arXiv)

We propose a simple three-stage approach to segment unseen objects in RGB images using their CAD models. Leveraging recent powerful foundation models, DINOv2 and Segment Anything, we create descriptors and generate proposals, including binary masks for a given input RGB image. By matching proposals with reference descriptors created from CAD models, we achieve precise object ID assignment along with modal masks. We experimentally demonstrate that our method achieves state-of-the-art results in CAD-based novel object segmentation, surpassing existing approaches on the seven core datasets of the BOP challenge by 19.8% AP using the same BOP evaluation protocol. Our source code is available at https://github.com/nv-nguyen/cnos.

Key facts. Cited by 86 papers in the map (data through 7 Oct 2026). Builds on 23 of its 28 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

23 of 28 references.

References · 23

  1. 2023Segment Anythingcited by 8,158
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2017Mask R-CNNcited by 7,259
  4. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  6. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  7. 2023Fast Segment Anythingcited by 286
  8. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  9. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  10. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  11. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  12. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
11 more
  1. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  2. 2020Unseen Object Instance Segmentation for Robotic Environmentscited by 85
  3. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  4. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  5. 2020Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentationcited by 64
  6. 2022Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusionscited by 54
  7. 2021Novel Class Discovery in Semantic Segmentationcited by 31
  8. 2021Unknown Object Segmentation from Stereo Imagescited by 16
  9. 2022PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Trackingcited by 15
  10. 2021Learning to Better Segment Objects from Unseen Classes with Unlabeled Videoscited by 9
  11. 20211st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021cited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 21; 2025: 31; 2026: 27.

86 papers.

Sort:

By area:

  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  2. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 115
  3. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 113
  4. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  5. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  6. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
  7. 2024SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priorscited by 53
  8. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 52
  9. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 47
  10. 2023ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformerscited by 45
  11. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  12. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
38 more
  1. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  2. 2024DITTO: Demonstration Imitation by Trajectory Transformationcited by 28
  3. 2024HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interactioncited by 25
  4. 2025VideoGen-Eval: Agent-based System for Video Generation Evaluationcited by 23
  5. 2025BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimationcited by 18
  6. 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentationcited by 17
  7. 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 13
  8. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  9. 2024Object Pose Estimation via the Aggregation of Diffusion Featurescited by 12
  10. 2024A Likelihood Ratio-Based Approach to Segmenting Unknown Objectscited by 12
  11. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  12. 2024IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videoscited by 11
  13. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  14. 2024High-resolution open-vocabulary object 6D pose estimationcited by 10
  15. 20256D Object Pose Tracking in Internet Videos for Robotic Manipulationcited by 10
  16. 2025GoTrack: Generic 6DoF Object Pose Refinement and Trackingcited by 10
  17. 2025XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexitycited by 7
  18. 2024Robust Bird's Eye View Segmentation by Adapting DINOv2cited by 6
  19. 2024Manual-PA: Learning 3D Part Assembly from Instruction Diagramscited by 6
  20. 2025ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Modelscited by 5
  21. 2025PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimationcited by 5
  22. 2024Diffusion Features for Zero-Shot 6DoF Object Pose Estimationcited by 4
  23. 2025Conditional Latent Diffusion Models for Zero-Shot Instance Segmentationcited by 4
  24. 2025RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimationcited by 4
  25. 2025SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulationcited by 4
  26. 2026SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wildcited by 4
  27. 2024Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Graspingcited by 3
  28. 2024BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguitiescited by 3
  29. 2024GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024cited by 3
  30. 2025PhysPose: Refining 6D Object Poses with Physical Constraintscited by 3
  31. 2025MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentationcited by 3
  32. 2025NOCTIS: Novel Object Cyclic Threshold based Instance Segmentationcited by 2
  33. 2026OSCAR: Open-Set CAD Retrieval from a Language Prompt and a Single Imagecited by 2
  34. 2025RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objectscited by 1
  35. 2025MR6D: Benchmarking 6D Pose Estimation for Mobile Robotscited by 1
  36. 2025See in Depth: Training-Free Surgical Scene Segmentation with Monocular Depth Priorscited by 1
  37. 2026IndustryShapes: An RGB-D Benchmark dataset for 6D object pose estimation of industrial assembly components and toolscited by 1
  38. 2026COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimationcited by 1

50 most cited of 86 All 86 (JSON)