Pith Number

pith:JULNET4B

pith:2026:JULNET4BKR2CMIOYAMTYKDJKSR

not attested not anchored not stored refs resolved

Sparse Code Uplifting for Efficient 3D Language Gaussian Splatting

Lovre Antonio Budimir, Nandita Vijaykumar, Steve Ryhner, Sven Lon\v{c}ari\'c, Yushi Guan

Sparse code uplifting from 2D images to 3D Gaussians delivers up to 400 times faster training for open-vocabulary scene understanding.

arxiv:2605.13600 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{JULNET4BKR2CMIOYAMTYKDJKSR}

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 method achieves up to 400× training speedup while being 3× more memory efficient during training compared to the state-of-the-art in rendering speed. Across multiple benchmarks, SCOUP matches or outperforms existing methods in open-vocabulary querying accuracy.

C2weakest assumption

That sparse codebook coefficients learned entirely from 2D image regions can be uplifted to 3D Gaussians via weighted multi-view aggregation and Top-K filtering without substantial loss of semantic accuracy or the need for per-scene language optimization.

C3one line summary

SCOUP decouples 2D sparse code learning from 3D Gaussian optimization to deliver up to 400x training speedup and 3x better memory efficiency while matching accuracy on open-vocabulary 3D queries.

References

43 extracted · 43 resolved · 2 Pith anchors

[1] GALA: Guided attention with language alignment for open vocabulary gaussian splatting 2026

[2] Barron, Ben Mildenhall, Dor Verbin, Pratul P 2022

[3] Gaussianeditor: Swift and controllable 3d editing with gaussian splatting.2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 21476–21485, 2023 2024

[4] URL https://doi.org/10.1109/CVPR52733 2024 · doi:10.1109/cvpr52733.2024.02022

[5] Occam’s lgs: An efficient approach for language gaussian splatting 2025

Receipt and verification

First computed	2026-05-18T02:44:22.942376Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8

Aliases

arxiv: 2605.13600 · arxiv_version: 2605.13600v1 · doi: 10.48550/arxiv.2605.13600 · pith_short_12: JULNET4BKR2C · pith_short_16: JULNET4BKR2CMIOY · pith_short_8: JULNET4B

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/JULNET4BKR2CMIOYAMTYKDJKSR \
  | 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: 4d16d24f8154742621d80327850d2a9445da6c13d8c16542979e51a885de64b8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "53369c60f99a84e2d7edfb95564554667a3fbe94f3656a8dcd1a53b0888d7f2d",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T14:35:31Z",
    "title_canon_sha256": "56ec71ba0809b46f7455cae7774de84fa51c0fa451e7e1cb1ca712a53841b1ed"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13600",
    "kind": "arxiv",
    "version": 1
  }
}