Pith Number

pith:TP44CXAX

pith:2026:TP44CXAXAIS52TH5YP5NP57C7B

not attested not anchored not stored refs resolved

FaceParts: Segmentation and Editing of Gaussian Splatting

Dominik Galus, Julia Farganus, Miko{\l}aj Czachorowski, Piotr Syga, Przemys{\l}aw Spurek, Tymoteusz Zapa{\l}a

Unsupervised segmentation decomposes Gaussian splatting avatars into editable facial parts like eyes and beards.

arxiv:2605.13853 v1 · 2026-03-25 · cs.GR · cs.AI · 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{TP44CXAXAIS52TH5YP5NP57C7B}

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 approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision... enabling precise editing and cross-avatar part swapping. Experiments... demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).

C2weakest assumption

That feature disentanglement followed by density-based clustering will reliably produce semantically coherent facial parts across varied identities and expressions without supervision or post-hoc tuning.

C3one line summary

FaceParts performs unsupervised segmentation of facial features in Gaussian Splatting avatars and supports precise editing and cross-avatar part transfer using feature disentanglement, density clustering, and FLAME anchoring.

References

48 extracted · 48 resolved · 0 Pith anchors

[1] Scaling Learning Algorithms Towards

[2] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month = 2025

[3] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month = 2025

[4] and Osindero, Simon and Teh, Yee Whye , journal =

[5] Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Receipt and verification

First computed	2026-05-17T23:39:19.579823Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9bf9c15c170225dd4cfdc3fad7f7e2f8764fe9550bf31582df8b47640f392a1b

Aliases

arxiv: 2605.13853 · arxiv_version: 2605.13853v1 · doi: 10.48550/arxiv.2605.13853 · pith_short_12: TP44CXAXAIS5 · pith_short_16: TP44CXAXAIS52TH5 · pith_short_8: TP44CXAX

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/TP44CXAXAIS52TH5YP5NP57C7B \
  | 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: 9bf9c15c170225dd4cfdc3fad7f7e2f8764fe9550bf31582df8b47640f392a1b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c1fa66eebbc68e74029036b3100f92078207ca8255bf340736cccd8b8b25cf17",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.GR",
    "submitted_at": "2026-03-25T21:34:06Z",
    "title_canon_sha256": "c67e045275443a97df434247443aa36a255ae06b3fda62ce94773791b49d2c54"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13853",
    "kind": "arxiv",
    "version": 1
  }
}