pith:HVQJEMZ2
LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction
Calibrating LiDAR intensity to reflectance and attaching it to Gaussians improves boundary consistency and reconstruction in complex lighting self-driving scenes.
arxiv:2603.12647 v3 · 2026-03-13 · cs.CV · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{HVQJEMZ23PIIRWQJ7DIKVT6EIY}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
On Complex Lighting scenes, our method surpasses OmniRe by 1.18 dB PSNR while using fewer Gaussians and shorter training time.
That LiDAR intensity can be reliably calibrated into a lighting-invariant reflectance channel that, when attached to each Gaussian, enforces boundary consistency with RGB without introducing new artifacts or requiring scene-specific tuning.
LR-SGS adds LiDAR reflectance as a lighting-invariant channel to guide salient Gaussian placement and density control, yielding higher PSNR than prior methods on Waymo complex-lighting scenes while using fewer Gaussians.
Formal links
Receipt and verification
| First computed | 2026-05-27T01:05:46.465608Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
3d6092333adbd088da09f8d0aacfc4462a3d4cf1feba3b497c161c3885a8b646
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/HVQJEMZ23PIIRWQJ7DIKVT6EIY \
| 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: 3d6092333adbd088da09f8d0aacfc4462a3d4cf1feba3b497c161c3885a8b646
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "41bb3f78e1fbed1696915720e4577362830585a874e9edd0b9f2f9bb0d1c7dc5",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-03-13T04:35:00Z",
"title_canon_sha256": "476ecf8e286989386d11945139dbb585c441ca4ca4e56bc17ef463a17b5145ea"
},
"schema_version": "1.0",
"source": {
"id": "2603.12647",
"kind": "arxiv",
"version": 3
}
}