BOP / 6D localization aggregation · aggregate

BOP AR

BOP Average Recall

Computes VSD, MSSD, and MSPD recall at multiple thresholds, then aggregates them into BOP's localization score.

AR is not a single distance. When reading BOP tables, distinguish AR_VSD, AR_MSSD, AR_MSPD, AR_D, and cross-dataset AR_C; they represent different aggregation levels.

Explore principles and formulas View related papers 53

Principle

What error does this metric penalize?

The formulas define the computation. The diagrams show whether the error concerns a 3D model, visible surfaces, the image plane, or aggregation across thresholds.

For each error function, first determine whether each predicted pose is correct at a given threshold, then compute recall over all annotated instances.

BOP addresses several application needs together, scoring visible surfaces, worst-case 3D deviation, and perceptible 2D deviation.

AR_D=\frac{AR_{VSD}+AR_{MSSD}+AR_{MSPD}}{3},\qquad AR_C=\operatorname*{avg}_{D\in\mathrm{core}} AR_D

AR_e averages recall over multiple correctness thresholds for the corresponding error function, including τ for VSD. Use the thresholds in the relevant BOP task configuration.

Illustration created for this site to explain the metric's error space; it does not show measured data or a figure from the original paper.

How to compute

Computation steps

01
Compute VSD, MSSD, and MSPD for each test instance.
02
Compute recall for each error at the BOP-defined thresholds, then obtain AR_e.
03
Average the three AR_e values to obtain dataset-level AR_D; when required, average over the core datasets to obtain AR_C.

Strength

What it is useful for

Covers occlusion, symmetry, 3D accuracy, and image projection together.
Aggregation over multiple thresholds is more stable than a single success threshold.

Caveat

Cautions when reading results

Whenever AR appears alone, check its dataset scope, task, and BOP year.
AR is used for object localization; detection uses AP. Keep the two distinct.

Paper atlas

Which papers report this metric?

Links are derived by normalizing the metric names used in each paper. Directly reported metrics are distinguished from metrics associated through a broader protocol.

Filter the paper library

53Related papers

53Directly reported

0Linked through a protocol

2026 Directly reported

AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment

CVPR · Anna Šárová Mikeštíková, Médéric Fourmy, Martin Cifka et al.

BOP AR

What error does this metric penalize?

Computation steps

What it is useful for

Cautions when reading results

Which papers report this metric?

AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment

COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation

ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors

CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generation

Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception

HRDexDB: A Paired Human-Robot Dataset for Cross-Embodiment Dexterous Grasping

IndustryShapes: An RGB-D Benchmark Dataset for 6D Object Pose Estimation of Industrial Assembly Components and Tools

InstantPose: Zero-Shot Instance-Level 6D Pose Estimation From a Single View

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

Pose Anything Anywhere: Model-free Object Poses from Arbitrary References

PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning

PoseGaussian: 6D Pose Estimation for Unseen Objects via Sparse-View Object-Level 3D Gaussian Splatting

WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion

Any6D: Model-free 6D Pose Estimation of Novel Objects

Co-op: Correspondence-based Novel Object Pose Estimation

Distilling 3D Distinctive Local Descriptors for 6D Pose Estimation

Multi-Layer Feature Exchange Transformer for Multi-View 6D Object Pose Estimation in Robot Bin Picking

Generalizable Zero-Shot Object Pose Estimation for Bin-Picking

iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting

Improving 6D Object Pose Estimation of Metallic Household and Industry Objects

MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation

One2Any: One-Reference 6D Pose Estimation for Any Object

Pos3R: 6D Pose Estimation for Unseen Objects Made Easy

RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base

Shape-Biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation

RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation

Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimation

RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects

RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking

SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow

UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

ZeroPose: CAD-Prompted Zero-Shot Object 6D Pose Estimation in Cluttered Scenes

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

FoundPose: Unseen Object Pose Estimation with Foundation Features

FreeZe: Training-free Zero-shot 6D Pose Estimation with Geometric and Vision Foundation Models

GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation

Learning Better Keypoints for Multi-Object 6DoF Pose Estimation

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images

MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation

NeRF-Feat: 6D Object Pose Estimation using Feature Rendering

NeuSurfEmb: A Complete Pipeline for Dense Correspondence-Based 6D Object Pose Estimation without CAD Models

Open-Vocabulary Object 6D Pose Estimation

PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments

Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation

SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation

ZS6D: Zero-Shot 6D Object Pose Estimation Using Vision Transformers

MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare

GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation

CosyPose: Consistent Multi-view Multi-object 6D Pose Estimation

EPOS: Estimating 6D Pose of Objects with Symmetries

Compare related metrics

VSD

MSSD

MSPD

BOP AP