Papers › Image generation with shortest path diffusion

Image generation with shortest path diffusion

1 Jun 2023arXiv:2306.00501archive 2025-07-28

Ayan Das, Stathi Fotiadis, Anil Batra, Farhang Nabiei, FengTing Liao, Sattar Vakili, Da-Shan Shiu, Alberto Bernacchia

The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently, a few studies introduced alternative ways of corrupting images in Diffusion Models, with an emphasis on blurring. However, these studies are purely empirical and it remains unclear what is the optimal procedure for corrupting an image. In this work, we hypothesize that the optimal procedure minimizes the length of the path taken when corrupting an image towards a given final state. We propose the Fisher metric for the path length, measured in the space of probability distributions. We compute the shortest path according to this metric, and we show that it corresponds to a combination of image sharpening, rather than blurring, and noise deblurring. While the corruption was chosen arbitrarily in previous work, our Shortest Path Diffusion (SPD) determines uniquely the entire spatiotemporal structure of the corruption. We show that SPD improves on strong baselines without any hyperparameter tuning, and outperforms all previous Diffusion Models based on image blurring. Furthermore, any small deviation from the shortest path leads to worse performance, suggesting that SPD provides the optimal procedure to corrupt images. Our work sheds new light on observations made in recent works and provides a new approach to improve diffusion models on images and other types of data.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.00501")

Code

Syntology Ran 12 of 22 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 4 ran · honoured contract; 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 22 samples from 1 repository, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mtkresearch/shortest-path-diffusion officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

22 samples harvested; 12 ran; 4 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · honoured contract
4ran · our draft was wrong
1ran · fixture could not drive it
3ran
10unverified

Licence: 0 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mtkresearch/shortest-path-diffusion. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

center_crop_arr mtkresearch/shortest-path-diffusion/guided_diffusion/image_datasets.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 8ab9a97df8161f31 · report
approx_standard_normal_cdf mtkresearch/shortest-path-diffusion/guided_diffusion/losses.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cfd76fd0d89574a4 · report
betas_for_alpha_bar mtkresearch/shortest-path-diffusion/guided_diffusion/gaussian_diffusion.py official repository ran · honoured contract Apache-2.0 (permissive) · 2ab2316ac6fdd869 · report
discretized_gaussian_log_likelihood mtkresearch/shortest-path-diffusion/guided_diffusion/losses.py official repository ran · our draft was wrong Apache-2.0 (permissive) · cd33283d615fb3d7 · report
get_named_beta_schedule mtkresearch/shortest-path-diffusion/guided_diffusion/gaussian_diffusion.py official repository ran · honoured contract Apache-2.0 (permissive) · a086d6286a40b889 · report
get_param_groups_and_shapes mtkresearch/shortest-path-diffusion/guided_diffusion/fp16_util.py official repository ran Apache-2.0 (permissive) · e41367ad14ff58fd · report
make_master_params mtkresearch/shortest-path-diffusion/guided_diffusion/fp16_util.py official repository ran Apache-2.0 (permissive) · e20dd5102da3b050 · report
normal_kl mtkresearch/shortest-path-diffusion/guided_diffusion/losses.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · cf2798b666b231ca · report
parse_resume_step_from_filename mtkresearch/shortest-path-diffusion/guided_diffusion/train_util.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 76313eaf1a6e8f2a · report
space_timesteps mtkresearch/shortest-path-diffusion/guided_diffusion/respace.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 9b6e4e070473e76f · report
unflatten_master_params mtkresearch/shortest-path-diffusion/guided_diffusion/fp16_util.py official repository ran Apache-2.0 (permissive) · 64fff1e30802b815 · report
zero_module mtkresearch/shortest-path-diffusion/guided_diffusion/nn.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 129b804760b3115f · report
avg_pool_nd mtkresearch/shortest-path-diffusion/guided_diffusion/nn.py official repository unverified Apache-2.0 (permissive) · ecd0fc28815b65ae · report
conv_nd mtkresearch/shortest-path-diffusion/guided_diffusion/nn.py official repository unverified Apache-2.0 (permissive) · fe4eb545bbb728e0 · report
create_classifier_and_diffusion mtkresearch/shortest-path-diffusion/guided_diffusion/script_util.py official repository unverified Apache-2.0 (permissive) · 654fcd52f4d13f0e · report
create_model mtkresearch/shortest-path-diffusion/guided_diffusion/script_util.py official repository unverified Apache-2.0 (permissive) · 135a415cce7947f5 · report
create_model_and_diffusion mtkresearch/shortest-path-diffusion/guided_diffusion/script_util.py official repository unverified Apache-2.0 (permissive) · f6a91281eec7c875 · report
create_named_schedule_sampler mtkresearch/shortest-path-diffusion/guided_diffusion/resample.py official repository unverified Apache-2.0 (permissive) · 9103fde01d82431f · report
make_output_format mtkresearch/shortest-path-diffusion/guided_diffusion/logger.py official repository unverified Apache-2.0 (permissive) · 95431cdc488516f0 · report
mpi_weighted_mean mtkresearch/shortest-path-diffusion/guided_diffusion/logger.py official repository unverified Apache-2.0 (permissive) · 76ce3502e9236621 · report
profile mtkresearch/shortest-path-diffusion/guided_diffusion/logger.py official repository unverified Apache-2.0 (permissive) · 8b1cfcd982d60968 · report
random_crop_arr mtkresearch/shortest-path-diffusion/guided_diffusion/image_datasets.py official repository unverified Apache-2.0 (permissive) · 53d5be4fdbcfac23 · report

Tasks

DeblurringImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections