pith. sign in
Pith Number

pith:MF2PILEK

pith:2026:MF2PILEKDCT4U3FWAVS5CC2FG2
not attested not anchored not stored refs resolved

Towards Generalized Image Manipulation Localization via Score-based Model

Bo Du, Ji-Zhe Zhou, Tianxin Xu, Xin Liu, Yunfei Wang, Zhe Yang, Zhiyu Lin

DiffIML approximates the score function of mask distributions to iteratively recover coherent manipulation masks from noise, improving generalization over discriminative methods.

arxiv:2605.16879 v1 · 2026-05-16 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{MF2PILEKDCT4U3FWAVS5CC2FG2}

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

DiffIML approximates the score function of mask distributions to iteratively recover coherent masks from noise, circumventing the brittleness of discriminative models and yielding consistent generalization improvements on diverse unseen datasets across eight non-generative and three generative benchmarks.

C2weakest assumption

The assumption that the learned score function, combined with edge supervision and error prior in a lightweight latent-space diffusion process, will reliably produce coherent masks without overfitting to training artifacts or requiring extensive per-dataset tuning.

C3one line summary

DiffIML applies score-based generative modeling to image manipulation localization, recovering coherent masks iteratively from noise to improve generalization on unseen manipulation types.

References

39 extracted · 39 resolved · 5 Pith anchors

[1] Analytic-dpm: an analytic estimate of the optimal reverse variance in diffusion probabilistic models 2022
[2] Xinru Chen, Chengbo Dong, Jiaqi Ji, Juan Cao, and Xirong Li. 2021. Image manipulation detection by multi-view multi-scale supervision. InProceedings of the IEEE/CVF International Conference on Compute 2021
[3] Chengbo Dong, Xinru Chen, Ruohan Hu, Juan Cao, and Xirong Li. 2023. MVSS- Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detec- tion.IEEE Transactions on Pattern Analysis and M 2023
[4] Jing Dong, Wei Wang, and Tieniu Tan. 2013. CASIA Image Tampering Detection Evaluation Database. In2013 IEEE China summit and international conference on signal and information processing. IEEE, 422–42 2013
[5] Bo Du, Xuekang Zhu, Xiaochen Ma, Chenfan Qu, Kaiwen Feng, Zhe Yang, Chi- Man Pun, Jian Liu, and Ji-Zhe Zhou. 2025. ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and L 2025

Formal links

1 machine-checked theorem link

Receipt and verification
First computed 2026-05-20T00:03:27.915983Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

6174f42c8a18a7ca6cb60565d10b4536b545bc34706b02b6dea4ec375db2b397

Aliases

arxiv: 2605.16879 · arxiv_version: 2605.16879v1 · doi: 10.48550/arxiv.2605.16879 · pith_short_12: MF2PILEKDCT4 · pith_short_16: MF2PILEKDCT4U3FW · pith_short_8: MF2PILEK
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/MF2PILEKDCT4U3FWAVS5CC2FG2 \
  | 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: 6174f42c8a18a7ca6cb60565d10b4536b545bc34706b02b6dea4ec375db2b397
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "c2a634d64184f07067a94ce47daa550e9b2729552775d3c9e6362b9a8cf3a06f",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T08:39:54Z",
    "title_canon_sha256": "b2ff810814c5769dcfc475c020bc82816a9f4b49f4ac4a2fd565c581bb248da4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16879",
    "kind": "arxiv",
    "version": 1
  }
}