Pith Number

pith:ITMISEQZ

pith:2026:ITMISEQZ7FRIDEWO2HJGPKWGZS

not attested not anchored not stored refs resolved

You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmaps

Anna Briotto, Endi Hysa, Lamberto Ballan, Marco Fiorucci, Riccardo Carraro

A lightweight U-Net reconstructs 128x128 faces from 16x16 inputs by weighting its loss with YOLO-World landmark heatmaps.

arxiv:2605.14166 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{ITMISEQZ7FRIDEWO2HJGPKWGZS}

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

Experiments on the aligned CelebA dataset demonstrate that the proposed loss consistently improves quantitative metrics and produces sharper, more realistic reconstructions.

C2weakest assumption

YOLO-World heatmaps generated directly from severely degraded 16x16 inputs remain accurate enough to serve as reliable spatial weights for the reconstruction loss without introducing misalignment artifacts.

C3one line summary

Lightweight U-Net for 8x face super-resolution uses YOLO-World landmark heatmaps as spatial loss weights to improve reconstruction on CelebA without extra networks or adversarial training.

References

32 extracted · 32 resolved · 0 Pith anchors

[1] Super-resolution image re- construction: a technical overview, 2003

[2] Deep learning for single image super-resolution: A brief review, 2019

[3] Photo-realistic single image super-resolution using a generative adversarial network, 2017

[4] Srflow: Learning the super-resolution space with normalizing flow, 2020

[5] Esrgan: Enhanced super-resolution generative adversar- ial networks, 2018

Receipt and verification

First computed	2026-05-17T23:39:11.408641Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

44d8891219f9628192ced1d267aac6ccbe16ae0c7d1c04466f4de20083da3fb5

Aliases

arxiv: 2605.14166 · arxiv_version: 2605.14166v1 · doi: 10.48550/arxiv.2605.14166 · pith_short_12: ITMISEQZ7FRI · pith_short_16: ITMISEQZ7FRIDEWO · pith_short_8: ITMISEQZ

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/ITMISEQZ7FRIDEWO2HJGPKWGZS \
  | 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: 44d8891219f9628192ced1d267aac6ccbe16ae0c7d1c04466f4de20083da3fb5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fbdc365c3a630f8b37d9ef0bb06a9eeddd7c9abd3b12c154193ecf33358a8f8b",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T22:41:23Z",
    "title_canon_sha256": "b83404ea7b26a8e28ea298fe538204cf63d151de465e1fbd181f524ae04932ab"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14166",
    "kind": "arxiv",
    "version": 1
  }
}