Pith Number

pith:KJSD3RHT

pith:2026:KJSD3RHTGVC4FXS2IRU7EFDO6Q

not attested not anchored not stored refs resolved

Training-Free Occluded Text Rendering via Glyph Priors and Attention-Guided Semantic Blending

Hongtian Wang, Jingqi Hou

A restarted dual-stream framework enables training-free occluded text rendering by preserving typography via glyph priors and attention-guided mask replacement.

arxiv:2605.16810 v1 · 2026-05-16 · 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{KJSD3RHTGVC4FXS2IRU7EFDO6Q}

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 representative occluded text scenarios demonstrate substantially improved text readability and competitive occlusion alignment, yielding more stable object-on-text compositions without any model fine-tuning.

C2weakest assumption

That the spectral glyph-prior from FreeText combined with token-conditioned attention can reliably localize the target text region and produce an anchor-aware hard fusion mask that allows clean K/V replacement without distorting typography or causing the occluder to drift.

C3one line summary

A restarted dual-stream inference approach with glyph priors and attention-guided masks improves occluded text rendering in pretrained diffusion models without fine-tuning.

References

20 extracted · 20 resolved · 2 Pith anchors

[1] arXiv preprint arXiv:2503.23461 (2025) 2025

[2] FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection 2026

[3] arXiv preprint arXiv:2305.10855 (2023) 7 2023

[4] Anytext: Multilingual visual text generation and editing 2023

[5] TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering 2023

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:23.506591Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

52643dc4f33545c2de5a4469f2146ef430be236bd3085d71c7a91e71bd20192e

Aliases

arxiv: 2605.16810 · arxiv_version: 2605.16810v1 · doi: 10.48550/arxiv.2605.16810 · pith_short_12: KJSD3RHTGVC4 · pith_short_16: KJSD3RHTGVC4FXS2 · pith_short_8: KJSD3RHT

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/KJSD3RHTGVC4FXS2IRU7EFDO6Q \
  | 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: 52643dc4f33545c2de5a4469f2146ef430be236bd3085d71c7a91e71bd20192e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6b222bd4162af6ddb633eda396d138458888a4bc99c8f85bed745bb145d2ce52",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T04:58:07Z",
    "title_canon_sha256": "87a83de8127fedb229b677efd3c67af0a9b7fd81b090b459232112f89678eeb7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16810",
    "kind": "arxiv",
    "version": 1
  }
}