Dexycb Eval

---
name: dexycb-eval
description: Evaluates joint perception and manipulation capabilities for hand-object interactions, specifically 2D detection, 6D object pose estimation, and 3D hand pose estimation on real-world RGB-D sequences. Use when the user wants to benchmark on DexYCB, or asks about evaluating this task. Reports precision-coverage.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2104.04631
  bibtex_key: chao2021dexycb
  confidence: medium
---

# dexycb-eval

> DexYCB: A Benchmark for Capturing Hand Grasping of Objects — Chao et al. (2021) (arXiv:2104.04631, 2021)

## What this evaluates

Evaluates joint perception and manipulation capabilities for hand-object interactions, specifically 2D detection, 6D object pose estimation, and 3D hand pose estimation on real-world RGB-D sequences.

## Datasets

- **DexYCB** — total 582000; splits: train (-1), val (-1), test (-1)

## Metrics

- `precision-coverage` **(primary)** — range: [0, 1]
  - Measures the trade-off between the precision of generated grasps and the coverage of successful grasp configurations across varying thresholds.
- `2D detection accuracy` — range: [0, 1]
  - Standard object and keypoint detection metrics (e.g., AP) evaluated on RGB images.
- `6D object pose error` — range: other
  - Translation and rotation error between predicted and ground-truth object poses.
- `3D hand pose error` — range: other
  - Joint position error between predicted and ground-truth 3D hand poses.

## Input / output format

**Input**: RGB-D frames captured from 8 synchronized camera views per frame.

**Output**: 2D bounding boxes and keypoints for hands/objects, 6D object pose matrices, 3D hand joint coordinates, and grasp proposals.

## Scoring recipe

```python
def compute_precision_coverage(pred_grasps, ref_grasps, threshold):
    correct = sum(1 for p in pred_grasps if any(distance(p, r) < threshold for r in ref_grasps))
    precision = correct / len(pred_grasps)
    coverage = correct / len(ref_grasps)
    return precision, coverage
# Plot precision vs coverage across thresholds
```

## Common pitfalls

- Models trained on DexYCB's controlled lab background do not generalize to in-the-wild images (e.g., COCO), showing significant performance drops.
- Object-specific landmarks require explicit handling to scale labeling across diverse object geometries.
- Occlusions during hand-object interaction complicate 2D keypoint and 3D pose estimation.

## Evidence (verbatim from paper)

> Figure 9: Precision-coverage curves for grasp generation on S0, S2, and S3.

We tested a DexYCB-trained model on COCO images [21] and observed an expected drop in performance.

## Citation

```bibtex
@misc{chao2021dexycb,
  title={DexYCB: A Benchmark for Capturing Hand Grasping of Objects},
  author={Chao et al. (2021)},
  year={2021},
  note={arXiv:2104.04631}
}
```

- arXiv: 2104.04631