Papers › Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration

Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration

2 Apr 2024arXiv:2404.02154archive 2025-07-28

Akshay Dudhane, Omkar Thawakar, Syed Waqas Zamir, Salman Khan, Fahad Shahbaz Khan, Ming-Hsuan Yang

All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement to tackle multiple degradations using the same model can lead to high-complexity designs with fixed configuration that lack the adaptability to more efficient alternatives. We propose DyNet, a dynamic family of networks designed in an encoder-decoder style for all-in-one image restoration tasks. Our DyNet can seamlessly switch between its bulkier and lightweight variants, thereby offering flexibility for efficient model deployment with a single round of training. This seamless switching is enabled by our weights-sharing mechanism, forming the core of our architecture and facilitating the reuse of initialized module weights. Further, to establish robust weights initialization, we introduce a dynamic pre-training strategy that trains variants of the proposed DyNet concurrently, thereby achieving a 50% reduction in GPU hours. Our dynamic pre-training strategy eliminates the need for maintaining separate checkpoints for each variant, as all models share a common set of checkpoints, varying only in model depth. This efficient strategy significantly reduces storage overhead and enhances adaptability. To tackle the unavailability of large-scale dataset required in pre-training, we curate a high-quality, high-resolution image dataset named Million-IRD, having 2M image samples. We validate our DyNet for image denoising, deraining, and dehazing in all-in-one setting, achieving state-of-the-art results with 31.34% reduction in GFlops and a 56.75% reduction in parameters compared to baseline models. The source codes and trained models are available at https://github.com/akshaydudhane16/DyNet.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 12 ran (6 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 12 samples that ran have no recorded date.

akshaydudhane16/dynet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 12 ran (6 instrument-failed) · 3 unverified 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
4ran; the contract check could not run
4ran
3unverified

Licence: 14 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 14 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from akshaydudhane16/dynet. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

akshaydudhane16/dynet official repository 15 samples, 12 ran (6 instrument-failed) · 3 unverified
contributions in 5 papers utils/imresize.py ran MIT (permissive) here; the stored copy is pointer only · b921438690ac017f · report fixture: signature in_length:int/0/int, out_length:int/0/int, scale:float/0/float, kernel:callable/0/?, kernel_width:float/0/float, antialiasing:bool/0/bool · returned tuple · level recorded 2026-09-24
crop_a_image utils/image_io.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 8ade57fc1fb950bb · report fixture: signature img:Image/0/?, d:int/0/int · returned Image · level recorded 2026-09-24
crop_img in 12 papers utils/image_utils.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 11c75b3b8bc61c21 · report fixture: signature image:ndarray/3/int, base:int/0/int · returned ndarray · level recorded 2026-09-24
crop_patch in 10 papers utils/image_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 86abcfa12b6612f0 · report fixture: signature im:ndarray/2/float, pch_size:int/0/int · returned ndarray · level recorded 2026-09-24
fix_scale_and_size in 5 papers utils/imresize.py ran MIT (permissive) here; the stored copy is pointer only · ee75635bb6c497f1 · report fixture: signature input_shape:tuple/1/int, output_shape:NoneType/0/?, scale_factor:float/0/float · returned tuple · level recorded 2026-09-24
get_position_from_periods in 59 papers utils/schedulers.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · cd569444547de84f · report fixture: signature iteration:int/0/int, cumulative_period:list/1/int · returned int · level recorded 2026-09-24
imresize in 28 papers utils/imresize.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · c38287d2acea0ce0 · report fixture: signature im:ndarray/3/float, scale_factor:float/0/float, output_shape:NoneType/0/?, kernel:NoneType/0/?, antialiasing:bool/0/bool, kernel_shift_flag:bool/0/bool · returned ndarray · level recorded 2026-09-24
linear_warmup_decay in 6 papers utils/schedulers.py ran MIT (permissive) here; the stored copy is pointer only · 442cb54f21dcfe50 · report fixture: signature warmup_steps:int/0/int, total_steps:int/0/int, cosine:bool/0/bool, linear:bool/0/bool · returned function · level recorded 2026-09-24
prepare_gt_img utils/image_io.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · e91553b51010dfd6 · report fixture: signature file_name:str/0/str, SOTS:bool/0/bool · returned ndarray · level recorded 2026-09-24
prepare_hazy_image utils/image_io.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 8564be766b7cda56 · report fixture: signature file_name:str/0/str · returned ndarray · level recorded 2026-09-24
to_3d in 66 papers
census: 3 implementations from 20 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
net/DyNet_large.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 82a15cc1e46f7e4d · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
to_4d in 69 papers net/DyNet_large.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · b20f2a5df739a59e · report fixture: signature x:Tensor/3/float, h:int/0/int, w:int/0/int · returned Tensor · level recorded, date not recorded
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils/val_utils.py unverified MIT (permissive) here; the stored copy is pointer only · 418284b6911ecae5 · report
compute_psnr_ssim in 5 papers utils/val_utils.py unverified MIT (permissive) · c25cfc27015346f2 · report
slice_image2patches in 5 papers utils/image_utils.py unverified MIT (permissive) here; the stored copy is pointer only · 779d9bd47765629e · report

Tasks

AllDecoderDenoisingImage DenoisingImage RestorationRain Removal

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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