Pith Number

pith:7OXKOFJX

pith:2026:7OXKOFJXTDCLXGPOV5OUKO32UY

not attested not anchored not stored refs resolved

Dual-Latent Collaborative Decoding for Fidelity-Perception Balanced Image Compression

Lingyu Zhu, Qi Mao, Siwei Ma, Zhengxue Cheng, Zijian Wang

Mixture of Decoder Experts coordinates scalar-quantized and vector-quantized latents to balance fidelity and perceptual quality across bitrates in learned image compression.

arxiv:2605.14391 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{7OXKOFJXTDCLXGPOV5OUKO32UY}

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

MoDE achieves a more favorable fidelity-perception balance than representative distortion-oriented, perception-oriented, generative, and dual-latent baselines across a wide bitrate range.

C2weakest assumption

That the Expert-Specific Enhancement and Cross-Expert Modulation modules can reliably coordinate SQ and VQ branches to produce consistent gains without introducing new artifacts or requiring per-dataset retuning that undermines the claimed generality.

C3one line summary

MoDE coordinates SQ fidelity experts and VQ perception experts via ESE and CEM modules to achieve superior fidelity-perception trade-offs in image compression over wide bitrate ranges.

References

37 extracted · 37 resolved · 0 Pith anchors

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

[2] Variational image compression with a scale hyperprior, 2018

[3] Joint autoregres- sive and hierarchical priors for learned image compression, 2018

[4] Energy compaction-based image compression using convolutional au- toencoder, 2019

[5] iwave: Cnn- based wavelet-like transform for image compression, 2019

Receipt and verification

First computed	2026-05-17T23:39:07.613665Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fbaea7153798c4bb99eeaf5d453b7aa61bcbf3112cd603e35a8367ce6aedb716

Aliases

arxiv: 2605.14391 · arxiv_version: 2605.14391v1 · doi: 10.48550/arxiv.2605.14391 · pith_short_12: 7OXKOFJXTDCL · pith_short_16: 7OXKOFJXTDCLXGPO · pith_short_8: 7OXKOFJX

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/7OXKOFJXTDCLXGPOV5OUKO32UY \
  | 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: fbaea7153798c4bb99eeaf5d453b7aa61bcbf3112cd603e35a8367ce6aedb716

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "aae8bdcfa182e178ff319c0dbcdfac37d5b13b3971e786a379554c97f9de5586",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T05:13:23Z",
    "title_canon_sha256": "6ab1635720d8a79cde35076786d37cf2f2a9e41cb3605946b3d5d8fbf6e659f6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14391",
    "kind": "arxiv",
    "version": 1
  }
}