Pith Number

pith:QDILO2T6

pith:2026:QDILO2T6VSNQJL674BLUYUYCHW

not attested not anchored not stored refs resolved

LiWi: Layering in the Wild

Dong Chen, Fang Li, Haoyang Tong, Jingling Fu, Junshi Huang, Lichen Ma, Luohang Liu, Xinyuan Shan, Yan Li, Yu He

Agent-driven synthesis creates over 100,000 layered natural images and trains models to decompose them with state-of-the-art accuracy.

arxiv:2605.14552 v1 · 2026-05-14 · 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{QDILO2T6VSNQJL674BLUYUYCHW}

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 framework achieves state-of-the-art (SoTA) performance in natural image decomposition, outperforming existing models in RGB L1 and Alpha IoU metrics.

C2weakest assumption

The Agent-driven Data Decomposition (ADD) pipeline produces high-quality, accurate layered ground truth for natural images without manual intervention, and the shadow-guided and degradation-restoration objectives correctly capture real-world illumination and boundary interactions.

C3one line summary

LiWi uses an agent-driven data synthesis pipeline to build the LiWi-100k dataset and a model with shadow-guided and degradation-restoration objectives that achieves SoTA performance on RGB L1 and Alpha IoU for natural image layering decomposition.

References

41 extracted · 41 resolved · 6 Pith anchors

[1] Layered neural atlases for consistent video editing.ACM Transactions on Graphics, 40(6):1–12, 2021 2021

[2] Text2live: Text-driven layered image and video editing 2022

[3] Shape- aware text-driven layered video editing 2023

[4] Resolution-robust large mask inpainting with fourier convolutions 2022

[5] Layerd: Decomposing raster graphic designs into layers 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:05.694877Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

80d0b76a7eac9b04afdfe0574c53023dafb94b863f264d97335c90c13b2592c1

Aliases

arxiv: 2605.14552 · arxiv_version: 2605.14552v1 · doi: 10.48550/arxiv.2605.14552 · pith_short_12: QDILO2T6VSNQ · pith_short_16: QDILO2T6VSNQJL67 · pith_short_8: QDILO2T6

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/QDILO2T6VSNQJL674BLUYUYCHW \
  | 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: 80d0b76a7eac9b04afdfe0574c53023dafb94b863f264d97335c90c13b2592c1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fb944439351b25fc081b3790fd311f9555dce1abe1a444099c13179f8f50bc25",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T08:30:34Z",
    "title_canon_sha256": "32a13d72cfe174d7f658cd8738b3dcc53975200e9b2c7687b3db867b3a431356"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14552",
    "kind": "arxiv",
    "version": 1
  }
}