Pith Number

pith:RQSG5Y2B

pith:2026:RQSG5Y2B2BFPEOI2WVKSOXBBAT

not attested not anchored not stored refs resolved

FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction

Gordon Guocheng Qian, Hao Li, Jiahao Luo, Jian Wang, Thuan Hoang Nguyen, Yinyu Nie

A feed-forward model reconstructs animatable 3D Gaussian head avatars from few unposed photos in seconds without per-subject optimization.

arxiv:2605.15320 v1 · 2026-05-14 · cs.GR · cs.CV · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{RQSG5Y2B2BFPEOI2WVKSOXBBAT}

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

FFAvatar reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds and sets a new standard for identity preservation, geometric consistency, and animation fidelity, outperforming the state-of-the-art LAM by a substantial 5.5 PSNR gain on the NeRSemble benchmark.

C2weakest assumption

The three-stage training curriculum on monocular video data with over 1M identities followed by multi-view fine-tuning produces priors that generalize to arbitrary few-shot unposed inputs without requiring offline pose or FLAME extraction.

C3one line summary

FFAvatar is a generalizable feed-forward framework that reconstructs high-quality animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds via Multi-View Query-Former and end-to-end FLAME prediction.

References

33 extracted · 33 resolved · 0 Pith anchors

[1] A morphable model for the synthesis of 3d faces.Seminal Graphics Papers: Pushing the Boundaries, Volume 2, pages 157–164, 2023 2023

[2] Generalizable and animatable gaussian head avatar 2024

[3] GPA- vatar: Generalizable and precise head avatar from image(s) 2024

[4] Black, and Timo Bolkart 2022

[5] Arcface: Additive angular margin loss for deep face recognition 2019

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T00:00:52.480050Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8c246ee341d04af2391ab555275c2104d00a3361cc446a42c898241701b23b4d

Aliases

arxiv: 2605.15320 · arxiv_version: 2605.15320v1 · doi: 10.48550/arxiv.2605.15320 · pith_short_12: RQSG5Y2B2BFP · pith_short_16: RQSG5Y2B2BFPEOI2 · pith_short_8: RQSG5Y2B

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/RQSG5Y2B2BFPEOI2WVKSOXBBAT \
  | 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: 8c246ee341d04af2391ab555275c2104d00a3361cc446a42c898241701b23b4d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ec498ea43cd1d203c2d4451c9c56041b3c2d507434d90a9db151e2a063ea244b",
    "cross_cats_sorted": [
      "cs.CV",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.GR",
    "submitted_at": "2026-05-14T18:33:49Z",
    "title_canon_sha256": "82bf35c1b3d769c5d7f62f5f4aad2e8ac5fbdf1da4a22dffce554e20ca733a23"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15320",
    "kind": "arxiv",
    "version": 1
  }
}