Pith Number

pith:3XU2JJFL

pith:2026:3XU2JJFLM4F7QSZHET7TUW6LEF

not attested not anchored not stored refs resolved

Adaptive Fused Prior Transfer for Controllable Generative Image Compression

Nam Ling, Yifei Pei, Ying Liu

AFP-GIC transfers fused priors from a frozen model so the decoder can predict them from compressed data and controls alone.

arxiv:2605.16817 v1 · 2026-05-16 · eess.IV · 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{3XU2JJFLM4F7QSZHET7TUW6LEF}

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

AFP-GIC reduces decoder latency by 18.1% and the overall parameter count by 31.10 million (20.5%) relative to DC-VIC while showing competitive PSNR and clearest perceptual gains in NIQE scores and very-low-bitrate visual comparisons on Kodak, CLIC2020, and DIV2K.

C2weakest assumption

The decoder can reliably predict a compatible fused prior from only the compressed representation and selected control variables, enabling prior-guided reconstruction without transmitting the prior (as described in the method overview and motivating analysis).

C3one line summary

AFP-GIC transfers adaptive fused priors from a frozen AdaCode model for prior-guided reconstruction in controllable generative image compression, cutting decoder latency 18.1% and parameters 20.5% versus DC-VIC with competitive PSNR and better NIQE at low bitrates.

References

53 extracted · 53 resolved · 1 Pith anchors

[1] J. Ballé, P. A. Chou, D. Minnen, S. Singh, N. Johnston, E. Agustsson, S. J. Hwang, and G. Toderici, “Nonlinear transform coding,”IEEE J. Sel. Topics Signal Process., vol. 15, no. 2, pp. 339–353, 2021 2021

[2] End-to-end optimized image compression, 2017

[3] Variational image compression with a scale hyper- prior, 2018

[4] Joint autore- gressive and hierarchical priors for learned image com- pression, 2018

[5] Conditional probability models for deep im- age compression, 2018

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:24.060810Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

dde9a4a4ab670bf84b2724ff3a5bcb2178fd3c79d0e033b0607d0aa5d7d1ca81

Aliases

arxiv: 2605.16817 · arxiv_version: 2605.16817v1 · doi: 10.48550/arxiv.2605.16817 · pith_short_12: 3XU2JJFLM4F7 · pith_short_16: 3XU2JJFLM4F7QSZH · pith_short_8: 3XU2JJFL

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/3XU2JJFLM4F7QSZHET7TUW6LEF \
  | 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: dde9a4a4ab670bf84b2724ff3a5bcb2178fd3c79d0e033b0607d0aa5d7d1ca81

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "69af543626f4abc3d5267dd078f7c9f81de2112a56fdb499de3f682720f45a28",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "eess.IV",
    "submitted_at": "2026-05-16T05:18:50Z",
    "title_canon_sha256": "a4a7daffa73c1cc3574022d370778e1c1c1b6c24d9bfe9318b684ef2285e34fc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16817",
    "kind": "arxiv",
    "version": 1
  }
}