pith:Z75F4ZUR
SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data
Models trained only on synthetic LiDAR scene flow data match or beat real supervised baselines on multiple benchmarks.
arxiv:2604.09411 v2 · 2026-04-10 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Z75F4ZURKII3XS7Q5PVYEEA4J6}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Models trained exclusively on SynFlow-4k generalize across multiple real-world benchmarks in a zero-shot regime, rivaling in-domain supervised baselines on nuScenes and outperforming state-of-the-art methods on TruckScenes by 31.8%.
The synthetic motion patterns generated by the pipeline are sufficiently representative of real-world kinematic distributions that models can learn domain-invariant priors without explicit domain adaptation.
SynFlow creates a 34-times larger synthetic LiDAR scene flow dataset that lets models trained only on simulation match or beat supervised real-data baselines on multiple benchmarks.
Receipt and verification
| First computed | 2026-07-29T01:25:37.084031Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
cffa5e66915211bbcbf0ebeb82101c4f903d6f26d218b91bfb05326899e848d7
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Z75F4ZURKII3XS7Q5PVYEEA4J6 \
| 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: cffa5e66915211bbcbf0ebeb82101c4f903d6f26d218b91bfb05326899e848d7
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "410d1cbdc6d7555edb70a37b6b2e004a412f9a472255dc7008635df5475a9cac",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-10T15:25:33Z",
"title_canon_sha256": "4fcca4be4135038bbfd733efc6b29b0f452be5467862f2fbfbaa011ae98e121b"
},
"schema_version": "1.0",
"source": {
"id": "2604.09411",
"kind": "arxiv",
"version": 2
}
}