Pith Number

pith:XNE6YCP4

pith:2026:XNE6YCP4ERMJVGL3WQNAQBAYRP

not attested not anchored not stored refs resolved

Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints

Haoyang Hu, Masataka Seo, Yen-Wei Chen

Point-based diffusion image editing stays natural by guiding steps with CLIP and constraining latents to the prior distribution.

arxiv:2605.13349 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{XNE6YCP4ERMJVGL3WQNAQBAYRP}

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

we introduce a CLIP-based model to evaluate and guide intermediate editing steps, ensuring that the generated results remain both semantically aligned. Additionally, we propose a prior-preservation loss that constrains the optimized latent code to stay within the sampling space of the diffusion prior, improving consistency with the original data distribution

C2weakest assumption

That the prior-preservation loss will keep edits natural without overly restricting editing freedom, and that CLIP can reliably guide semantic alignment during intermediate diffusion steps without introducing new artifacts.

C3one line summary

Introduces CLIP guidance and prior-preservation loss to constrain point-based diffusion image edits within the model's sampling distribution for more consistent results.

References

36 extracted · 36 resolved · 1 Pith anchors

[1] Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints 2026 · arXiv:2605.13349

[2] Point-based method Point-based image editing was initially introduced by DragGAN[1], which alternates iterative optimization within the latent space

[3] Motion su- pervision often struggles to distinguish between local and global tar- gets

[4] Therefore, we consider introducing text guidance based on reward feedback to control the gradient direction of motion supervi- sion

[5] Compare with SOTA methods To validate the effectiveness of our proposed method, we design a set of comparative experiments focusing on Prior-Preserving Reg- ularization (PPR)

Cited by

1 paper in Pith

Drag within Prior Distribution: Text-Conditioned Point-Based Image Editing within Distribution Constraints

Receipt and verification

First computed	2026-05-18T02:44:48.299364Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bb49ec09fc24589a997bb41a0804188bd8ec85407f7843bcc4ac90ffd037f385

Aliases

arxiv: 2605.13349 · arxiv_version: 2605.13349v1 · doi: 10.48550/arxiv.2605.13349 · pith_short_12: XNE6YCP4ERMJ · pith_short_16: XNE6YCP4ERMJVGL3 · pith_short_8: XNE6YCP4

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/XNE6YCP4ERMJVGL3WQNAQBAYRP \
  | 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: bb49ec09fc24589a997bb41a0804188bd8ec85407f7843bcc4ac90ffd037f385

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "61ba37cb814c5d887b1171cde30f3eecec5ce0325ab880cdb18d544f381b071b",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T11:05:31Z",
    "title_canon_sha256": "1197b31a5c0a83e36ce9d53dea2c2d0fc3a9be0695344f710752003f93746aef"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13349",
    "kind": "arxiv",
    "version": 1
  }
}