SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.19802 · 2026

Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems

Santiago Segarra, Morteza Mardani, Nicolas Zilberstein

arXiv · PDF · Open in the Atlas

Code that ran

12 of 17 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 failures of our instrument; 5 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2606.19802.json · badge: /api/ran/2606.19802.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
nzilberstein/Flow-map-denoisers canonical (classifier label)
classifier basis: census
12 ran · 5 no recorded run
FunctionStatusWhere it lives
compute_psnr Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/run_baselines.py
pointer only (licence: NONE) · get_code("dbcbcd124896817f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

discover Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/pnp_metrics.py
pointer only (licence: NONE) · get_code("9dfebc5e70548027")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

discover Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/run_ablation_steps.py
pointer only (licence: NONE) · get_code("4398ee04a40717c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_time Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/dnnlib/util.py
pointer only (licence: NONE) · get_code("674eca7b9e1b6439")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_time_brief Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/dnnlib/util.py
pointer only (licence: NONE) · get_code("32af001972a0699f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nzilberstein/Flow-map-denoisers/run_baselines.py
pointer only (licence: NONE) · get_code("76cfa754c0ba6a8a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_args Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/baselines/flow_priors.py
pointer only (licence: NONE) · get_code("13869e891e92462f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_folder Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/pnp_metrics.py
pointer only (licence: NONE) · get_code("0b75bba426fd81f4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_folder Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/run_ablation_steps.py
pointer only (licence: NONE) · get_code("b55b7a89431a7d9e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_int_list Ran
ran, honoured the contract we drafted
nzilberstein/Flow-map-denoisers/train_mf.py
pointer only (licence: NONE); the stored copy get_code serves, from newbeeer/stf, is pointer only (licence: NONE) · get_code("cacd4f6ec202d9b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sorted_pt_files Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/compute_metrics.py
pointer only (licence: NONE) · get_code("17c297791fba3876")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sorted_restored_pngs Ran
ran; our contract draft was wrong, not the code
nzilberstein/Flow-map-denoisers/pnp_metrics.py
pointer only (licence: NONE) · get_code("3a214ac6d02ca1e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ask_yes_no Not yet run
unverified (harvested, no recorded run)
nzilberstein/Flow-map-denoisers/dnnlib/util.py
pointer only (licence: NONE) · get_code("9d31d2c4cd16bb2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

compute_is Not yet run
unverified (harvested, no recorded run)
nzilberstein/Flow-map-denoisers/metrics/inception_score.py
pointer only (licence: NONE) · get_code("290651a70c4fa3f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

compute_lpips Not yet run
unverified (harvested, no recorded run)
nzilberstein/Flow-map-denoisers/run_baselines.py
pointer only (licence: NONE) · get_code("af257f75666c79e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

detect_model Not yet run
unverified (harvested, no recorded run)
nzilberstein/Flow-map-denoisers/compute_metrics.py
pointer only (licence: NONE) · get_code("90ae41e6c0cb9fff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_gt_dataset Not yet run
unverified (harvested, no recorded run)
nzilberstein/Flow-map-denoisers/compute_metrics.py
pointer only (licence: NONE) · get_code("c5b7201cf83d7e4f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nzilberstein/Flow-map-denoisers when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 3 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
format_time 73 other papers
71 dated earlier, 1 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 70 more not named here
ask_yes_no 69 other papers
68 dated earlier, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 66 more not named here
format_time_brief 68 other papers
66 dated earlier, 1 later, 1 undated
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 65 more not named here
parse_int_list 37 other papers
36 dated earlier, 1 later
2206.00364 (2022-06)
Elucidating the Design Space of Diffusion-Based Generative Models
2302.00670 (2023-02)
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
2302.04265 (2023-02)
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
and 34 more not named here
grid 1 other paper
1 dated earlier
1912.04958 (2019-12)
Analyzing and Improving the Image Quality of StyleGAN

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images. Existing approaches either commit to a single operating point on this distortion perception (DP) frontier or require paired-data supervision, auxiliary models, or hyperparameter tuning of the sampler to access different points. We show that flow map models, a recent extension of flow matching for few-step sampling that learns an average field, implicitly define a one-parameter family of denoisers that continuously spans the DP frontier. The lookahead parameter t acts as a control knob between the MMSE and perceptual regimes. For Gaussian targets, we prove that varying t exactly recovers the optimal DP frontier; for natural images, we observe similar behavior empirically. Within a Plug-and-Play solver, the same mechanism extends to general inverse problems, where it controls a tradeoff between perceptual alignment and data consistency. Despite the lack of exact optimality guarantees in this setting, a single trained flow map spans the DP tradeoff, matching or exceeding specialized baselines at both extremes. Extensive experiments on CelebA (128 × 128) and AFHQ (256 × 256) across several linear and nonlinear inverse tasks validate our findings. Code is available in https://github.com/nzilberstein/Flow-map-denoisers Image restoration is a highly ill-posed inverse problem: a single degraded observation can correspond to a vast set of plausible clean images. Standard regression approaches that minimize mean squared error (MSE) approximate the conditional expectation (Ongie et al., 2020), achieving minimum distortion at the cost of over-smoothed reconstructions that lack fine detail. In contrast, posterior sampling techniques (Kawar et al., 2021) produce realistic-looking solutions at the cost of higher distortion. This inherent compromise is formalized by the distortion-perception (DP) tradeoff (Blau and Michaeli, 2018;Freirich et al., 2021). Because the ideal balance between low distortion and high perceptual quality is strictly user-dependent, designing a single model capable of traversing the DP plane at inference time remains a central challenge in computational imaging. Most existing methods commit to a single operating point in the DP plane, either targeting minimum distortion through supervised regression (Dong et al., 2015;Terris et al., 2026), or minimum perception by leveraging recent generative models as priors (Pokle et al., 2024;Chung et al., 2023;Kadkhodaie and Simoncelli, 2021) to draw samples from the posterior. A few recent works based on data-dependent flow models aim to traverse the DP plane (Ohayon et al., 2025; Delbracio and Preprint.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2606.19802")
get_code_for_paper("2606.19802")
have("2606.19802")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2606.19802.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2606.19802.svg)](https://syntology.ai/paper/2606.19802)

Connect an agent — have() is free.