pith:4EZO73MZ
Neural Surface Reconstruction from Sparse Views Using Epipolar Geometry
EpiS reconstructs surfaces from sparse multi-view images by guiding fine-grained epipolar feature aggregation with coarse cost-volume features.
arxiv:2406.04301 v5 · 2024-06-06 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{4EZO73MZIQYBKJHFPIVBF3FI4Q}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
EpiS significantly outperforms state-of-the-art generalizable surface reconstruction methods under sparse-view settings, while maintaining strong generalization without per-scene optimization.
That coarse cost-volume features can reliably guide fine-grained epipolar feature aggregation and that a pretrained monocular depth model supplies unbiased scale-invariant global and local constraints that align with the multi-view epipolar geometry (abstract, paragraph on geometry regularization strategy).
EpiS improves generalizable neural surface reconstruction from sparse views by guiding epipolar feature aggregation with cost volumes, using an epipolar transformer, and applying pretrained monocular depth constraints, outperforming prior methods on DTU and BlendedMVS.
Formal links
Cited by
Receipt and verification
| First computed | 2026-08-05T01:36:10.717819Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
e132efed9944301524e57a2a12eca8e424c0cfdda407fd9b0a3881514e37434b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/4EZO73MZIQYBKJHFPIVBF3FI4Q \
| 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: e132efed9944301524e57a2a12eca8e424c0cfdda407fd9b0a3881514e37434b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "2b13dcee76c35440ddd0c30d54853e6b3482012ed1175abdf784ffd3a2095771",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2024-06-06T17:47:48Z",
"title_canon_sha256": "ddb2a4e1c358be5bb42ec126c0098e73777048760203c8a9febebcfe4046773e"
},
"schema_version": "1.0",
"source": {
"id": "2406.04301",
"kind": "arxiv",
"version": 5
}
}