pith:HG6E6ZSF
Diffusion Restore: Real-Time Markov Chain Monte Carlo Light Transport
Diffusion Restore enables real-time MCMC light transport by using nonreversible diffusion-based dynamics without Metropolis adjustment.
arxiv:2605.08916 v3 · 2026-05-09 · cs.CE · cs.NA · math.NA · math.PR
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{HG6E6ZSFRV7VFY5DASLWOGHFFK}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Empirically, we demonstrate across diverse scenes that Diffusion Restore outperforms all existing MCMC light transport methods and establishes a new state of the art. In addition, we present a GPU implementation in ray tracing and compute shaders and achieve real-time frame rates.
That the chosen nonreversible diffusion-based local dynamics remain valid and unbiased for light transport integrals when Metropolis adjustment is completely avoided, relying only on the theoretical justification provided for the Restore framework extension.
Diffusion Restore uses nonreversible diffusion dynamics in the Restore MCMC framework to achieve faster, unbiased light transport sampling that outperforms prior MCMC methods and runs in real time on GPU.
Receipt and verification
| First computed | 2026-05-21T01:05:20.771859Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
39bc4f66458d7f52e3a304976718e52a80dd9c89f06f3bc9ffa1db0d1361b12b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/HG6E6ZSFRV7VFY5DASLWOGHFFK \
| 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: 39bc4f66458d7f52e3a304976718e52a80dd9c89f06f3bc9ffa1db0d1361b12b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "4128a9a541a62d5ca4b47c9209cea83d5ef9c6c5c1a7b20725e45a79cecaec21",
"cross_cats_sorted": [
"cs.NA",
"math.NA",
"math.PR"
],
"license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
"primary_cat": "cs.CE",
"submitted_at": "2026-05-09T12:31:52Z",
"title_canon_sha256": "7cd653f8d67452b9a5a1b62ce951b35a9576c41173f781cfb8da5f3453a5ff69"
},
"schema_version": "1.0",
"source": {
"id": "2605.08916",
"kind": "arxiv",
"version": 3
}
}