Image Reconstruction

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

12 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

5 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 712 papers with code (2,143 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• High-Resolution Image Synthesis with Latent Diffusion Models
  20 Dec 2021 41 repositories listed Syntology ran 19 of 28 samples · 9 unverified · 5 pointer-only (licence)
  By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
• Unsupervised Monocular Depth Estimation with Left-Right Consistency
  13 Sep 2016 16 repositories listed Syntology ran 3 of 12 samples · 9 unverified · 5 pointer-only (licence)
  Learning based methods have shown very promising results for the task of depth estimation in single images.
• Digging Into Self-Supervised Monocular Depth Estimation
  4 Jun 2018 15 repositories listed Syntology ran 17 of 24 samples · 7 unverified · 6 pointer-only (licence)
  Per-pixel ground-truth depth data is challenging to acquire at scale.
• Universal Style Transfer via Feature Transforms
  23 May 2017 15 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural…
• Taming Transformers for High-Resolution Image Synthesis
  17 Dec 2020 13 repositories listed Syntology ran 6 of 6 samples · 0 unverified · 4 pointer-only (licence)
  We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images.
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
  21 Nov 2018 13 repositories listed Syntology ran 2 of 5 samples · 3 unverified
  Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applications where it is currently prohibitively…
• MaskGIT: Masked Generative Image Transformer
  8 Feb 2022 9 repositories listed Syntology ran 14 of 21 samples · 7 unverified · 4 pointer-only (licence)
  At inference time, the model begins with generating all tokens of an image simultaneously, and then refines the image iteratively conditioned on the previous generation.
• SwinIR: Image Restoration Using Swin Transformer
  23 Aug 2021 9 repositories listed Syntology ran 30 of 45 samples · 15 unverified · 5 pointer-only (licence)
  In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection.
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
  30 Nov 2021 7 repositories listed
  Machine Learning methods can learn how to reconstruct Magnetic Resonance Images and thereby accelerate acquisition, which is of paramount importance to the clinical workflow.
• Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
  4 Oct 2017 7 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 1 pointer-only (licence)
  However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results.
• Unifying Vision, Text, and Layout for Universal Document Processing
  5 Dec 2022 5 repositories listed Syntology ran 4 of 17 samples · 13 unverified · 3 pointer-only (licence)
  UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation.
• Vector-quantized Image Modeling with Improved VQGAN
  9 Oct 2021 5 repositories listed Syntology ran 3 of 9 samples · 6 unverified
  Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively.
• Homotopic Gradients of Generative Density Priors for MR Image Reconstruction
  14 Aug 2020 5 repositories listed
  Deep learning, particularly the generative model, has demonstrated tremendous potential to significantly speed up image reconstruction with reduced measurements recently.
• Autoregressive Image Generation using Residual Quantization
  3 Mar 2022 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  However, we postulate that previous VQ cannot shorten the code sequence and generate high-fidelity images together in terms of the rate-distortion trade-off.
• Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
  15 Nov 2021 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  The HSI representations are highly similar and correlated across the spectral dimension.
• Improving generative adversarial network inversion via fine-tuning GAN encoders
  23 Aug 2021 4 repositories listed
  To address these issues, we proposed a self-supervised method to pre-train and fine-tune GAN encoders.
• ReconResNet: Regularised Residual Learning for MR Image Reconstruction of Undersampled Cartesian and Radial Data
  16 Mar 2021 4 repositories listed
  It has been shown that the proposed framework can successfully reconstruct even for an acceleration factor of 20 for Cartesian (0.
• Accelerated MRI with Un-trained Neural Networks
  6 Jul 2020 4 repositories listed
  Convolutional Neural Networks (CNNs) are highly effective for image reconstruction problems.
• Gradient Origin Networks
  6 Jul 2020 4 repositories listed Syntology ran 5 of 14 samples · 9 unverified · 1 pointer-only (licence)
  This paper proposes a new type of generative model that is able to quickly learn a latent representation without an encoder.
• Probabilistic Autoencoder
  9 Jun 2020 4 repositories listed Syntology ran 1 of 13 samples · 12 unverified
  The PAE is fast and easy to train and achieves small reconstruction errors, high sample quality, and good performance in downstream tasks.
• Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
  2 Oct 2019 4 repositories listed Syntology ran 5 of 6 samples · 1 unverified
  A promising approach is to learn a latent representation together with the control policy.
• Implicit Generation and Generalization in Energy-Based Models
  20 Mar 2019 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train.
• Towards real-time unsupervised monocular depth estimation on CPU
  29 Jun 2018 4 repositories listed
  To tackle this issue, in this paper we propose a novel architecture capable to quickly infer an accurate depth map on a CPU, even of an embedded system, using a pyramid of features extracted from a single input image.
• Efficient and accurate inversion of multiple scattering with deep learning
  18 Mar 2018 4 repositories listed
  Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography.
• Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction
  5 Dec 2017 4 repositories listed
  In particular, the proposed architecture embeds the structure of the traditional iterative algorithms, efficiently modelling the recurrence of the iterative reconstruction stages by using recurrent hidden connections…
• Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network
  18 Jul 2017 4 repositories listed
  A combination of Deep CNNs and Skip connection layers is used as a feature extractor for image features on both local and global area.
• A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction
  8 Apr 2017 4 repositories listed
  Firstly, we show that when each 2D image frame is reconstructed independently, the proposed method outperforms state-of-the-art 2D compressed sensing approaches such as dictionary learning-based MR image reconstruction,…
• A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction
  1 Mar 2017 4 repositories listed
  The acquisition of Magnetic Resonance Imaging (MRI) is inherently slow.
• Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
  3 Apr 2024 3 repositories listed Syntology ran 5 of 11 samples · 6 unverified
  We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from…
• Modality Cycles with Masked Conditional Diffusion for Unsupervised Anomaly Segmentation in MRI
  30 Aug 2023 3 repositories listed
  Furthermore, we combine image translation with a masked conditional diffusion model, which attempts to `imagine' what tissue exists under a masked area, further exposing unknown patterns as the generative model fails to…

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.