pith:UPRKJDSO
SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
SplatWeaver learns to assign different numbers of 3D Gaussians to different scene regions for better feed-forward novel view synthesis.
arxiv:2605.07287 v2 · 2026-05-08 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UPRKJDSOKGMR2O65WNH7G4SAKA}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
SplatWeaver consistently outperforms state-of-the-art methods, delivering more faithful novel-view renderings with fewer Gaussian primitives.
That the combination of cardinality experts, pixel-level routing, high-frequency prior, and routing regularization will stably produce complexity-aware allocations that generalize across scenes without overfitting or requiring per-scene optimization.
SplatWeaver dynamically allocates Gaussian primitives via cardinality experts and pixel-level routing guided by high-frequency cues for improved generalizable novel view synthesis.
Formal links
Receipt and verification
| First computed | 2026-05-22T01:04:05.242103Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
a3e2a48e4e51991d3bddb34ff37240501873e8be3289561d92b59f9d67e48efb
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UPRKJDSOKGMR2O65WNH7G4SAKA \
| 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: a3e2a48e4e51991d3bddb34ff37240501873e8be3289561d92b59f9d67e48efb
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "b4d4f4ccd1dc83908d2487d58a8e1842d76378449f0b55c5a1f2f20447c360fc",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-05-08T05:51:34Z",
"title_canon_sha256": "f40302343d58d01e6837475453f67aafbcb8e935d2b8b43a7cbdb85df9329d84"
},
"schema_version": "1.0",
"source": {
"id": "2605.07287",
"kind": "arxiv",
"version": 2
}
}