Pith Number

pith:V4JMSFK6

pith:2021:V4JMSFK6F45TDOC6NPE4ETERC6

not attested not anchored not stored refs resolved

BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View

Dalong Du, Guan Huang, Junjie Huang, Yun Ye, Zheng Zhu

BEVDet detects 3D objects in bird-eye-view by reusing standard modules plus custom data augmentation and upgraded NMS.

arxiv:2112.11790 v3 · 2021-12-22 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{V4JMSFK6F45TDOC6NPE4ETERC6}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

BEVDet-Base scores 39.3% mAP and 47.2% NDS, significantly exceeding all published results. With a comparable inference speed, it surpasses FCOS3D by a large margin of +9.8% mAP and +10.0% NDS.

C2weakest assumption

That the exclusive data augmentation strategy and upgraded NMS will deliver consistent gains on unseen environments and datasets without introducing hidden biases or requiring extensive per-dataset retuning.

C3one line summary

BEVDet achieves 39.3% mAP and 47.2% NDS on nuScenes val set with a fast BEV-based multi-camera 3D detector that outperforms FCOS3D while using far less compute in its tiny variant.

References

64 extracted · 64 resolved · 2 Pith anchors

[1] In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2020

[2] IEEE Transactions on Pattern Analysis and Machine In- telligence (2019) 2019

[3] In: Proceedings of the European Conference on Computer Vision 2020

[4] In: Pro- ceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019

[5] In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2020

Formal links

2 machine-checked theorem links

Cited by

30 papers in Pith

Fast-BEV++: Fast by Algorithm, Deployable by Design

Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations

VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction

RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection

BePo: Dual Representation for 3D Occupancy Prediction

Receipt and verification

First computed	2026-05-17T23:38:52.339275Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

af12c9155e2f3b31b85e6bc9c24c91178aa5ca4c79c1d5eb6e50a9faa3f6c61e

Aliases

arxiv: 2112.11790 · arxiv_version: 2112.11790v3 · doi: 10.48550/arxiv.2112.11790 · pith_short_12: V4JMSFK6F45T · pith_short_16: V4JMSFK6F45TDOC6 · pith_short_8: V4JMSFK6

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/V4JMSFK6F45TDOC6NPE4ETERC6 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: af12c9155e2f3b31b85e6bc9c24c91178aa5ca4c79c1d5eb6e50a9faa3f6c61e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b4e975b47487059937fd96bd00e5f76acd9f85c939ce8e73d436f37c498caaa7",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2021-12-22T10:48:06Z",
    "title_canon_sha256": "22725f03a1294bed6ad437d3134bc6201141149ed621d202df7fb1a5cc5d1244"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2112.11790",
    "kind": "arxiv",
    "version": 3
  }
}