Pith Number

pith:LWY2BP6U

pith:2026:LWY2BP6UWURWV2VH2BVMDM2Z43

not attested not anchored not stored refs resolved

Generative Texture Diversification of 3D Pedestrians for Robust Autonomous Driving Perception

Ahmed Abdullah, Arka Bhowmick, Enes Ozeren, Oliver Wasenmuller

Synthesizing diverse facial textures on one 3D pedestrian base asset improves 2D detection robustness but exposes geometric sensitivities in 3D point-cloud models.

arxiv:2605.13755 v1 · 2026-05-13 · 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{LWY2BP6UWURWV2VH2BVMDM2Z43}

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

Our findings demonstrate that controlled synthetic diversification improves robustness in 2D detection while revealing the sensitivity of 3D perception models to geometric domain gaps.

C2weakest assumption

That automatically mapping StyleGAN2-generated textures onto 3D meshes produces appearance variations that are realistic enough to improve robustness without introducing mapping artifacts or distribution shifts that undermine the detection gains.

C3one line summary

Generative texture synthesis from StyleGAN2 diversifies 3D pedestrian assets from a single base model, improving robustness in 2D object detection while exposing 3D perception models' sensitivity to geometric domain gaps.

References

26 extracted · 26 resolved · 2 Pith anchors

[1] Boosting few-shot detection with large language models and layout-to-image synthesis 2024

[2] Ffhq-uv: Normalized facial uv-texture dataset for 3d face reconstruction, 2023 2023

[3] Vir- tual kitti 2, 2020 2020

[4] Data augmentation for object detec- tion via controllable diffusion models 2024

[5] Virtual worlds as proxy for multi-object tracking anal- ysis, 2016 2016

Receipt and verification

First computed	2026-05-18T02:44:16.345625Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5db1a0bfd4b5236aeaa7d06ac1b359e6f93c8692fa64519b4d638fa4a89ef43a

Aliases

arxiv: 2605.13755 · arxiv_version: 2605.13755v1 · doi: 10.48550/arxiv.2605.13755 · pith_short_12: LWY2BP6UWURW · pith_short_16: LWY2BP6UWURWV2VH · pith_short_8: LWY2BP6U

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/LWY2BP6UWURWV2VH2BVMDM2Z43 \
  | 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: 5db1a0bfd4b5236aeaa7d06ac1b359e6f93c8692fa64519b4d638fa4a89ef43a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6bda4390a62b3dcb19689d10f918a7aeee2f1b97c6f90879a9e25690734f1ab8",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T16:35:50Z",
    "title_canon_sha256": "9b61a8c5369849bf6cfe4659d3781b1f53e955d52008b021b186021ee9bbf4b4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13755",
    "kind": "arxiv",
    "version": 1
  }
}