Methods › Computer Vision › Image Model Blocks › Spatial Transformer
Spatial Transformer
Introduced by Max Jaderberg et al. in Spatial Transformer Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Spatial Transformer is an image model block that explicitly allows the spatial manipulation of data within a convolutional neural network. It gives CNNs the ability to actively spatially transform feature maps, conditional on the feature map itself, without any extra training supervision or modification to the optimisation process. Unlike pooling layers, where the receptive fields are fixed and local, the spatial transformer module is a dynamic mechanism that can actively spatially transform an image (or a feature map) by producing an appropriate transformation for each input sample. The transformation is then performed on the entire feature map (non-locally) and can include scaling, cropping, rotations, as well as non-rigid deformations.
The architecture is shown in the Figure to the right. The input feature map U is passed to a localisation network which regresses the transformation parameters θ. The regular spatial grid G over V is transformed to the sampling grid T_θ(G), which is applied to U, producing the warped output feature map V. The combination of the localisation network and sampling mechanism defines a spatial transformer.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: Spatially-Aware Transformer; word-level spatial transformer; Ring-based Spatial Transformer; Hierarchical Spatial Transformer; Spatial Grouping Transformer Block; Spatial Planning Transformers (SPT); Spatial-Temporal Parallel Transformer; Spatial-Temporal Transformer (STTran).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 169 · with a code link: 73 · where Syntology ran a sample: 12 (9 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (12 of 169 tagged: 9 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 169, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception 16 Jun 2025 · 0 repositories · arXiv:2506.13501
-
GuidedMorph: Two-Stage Deformable Registration for Breast MRI 19 May 2025 · 0 repositories · arXiv:2505.13414
-
EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition 14 Jan 2025 · 1 repository · arXiv:2501.08199
-
Neural encoding with affine feature response transforms 7 Jan 2025 · 1 repository · arXiv:2501.03741
-
A novel deep learning approach for facial emotion recognition: application to detecting emotional responses in elderly individuals with Alzheimer’s disease 30 Dec 2024 · 1 repository
-
Fixing the Perspective: A Critical Examination of Zero-1-to-3 24 Nov 2024 · 0 repositories · arXiv:2411.15706
-
ESC-MISR: Enhancing Spatial Correlations for Multi-Image Super-Resolution in Remote Sensing 7 Nov 2024 · 0 repositories · arXiv:2411.04706
-
Spatial Transformers for Radio Map Estimation 2 Nov 2024 · 0 repositories · arXiv:2411.01211
-
Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction 24 Oct 2024 · 0 repositories · arXiv:2410.18962
-
Disambiguating Monocular Reconstruction of 3D Clothed Human with Spatial-Temporal Transformer 21 Oct 2024 · 0 repositories · arXiv:2410.16337
-
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping 17 Sep 2024 · 1 repository · arXiv:2409.11316
-
Automatic facial axes standardization of 3D fetal ultrasound images 4 Sep 2024 · 0 repositories · arXiv:2409.02826
-
Improved 3D Whole Heart Geometry from Sparse CMR Slices 14 Aug 2024 · 1 repository · arXiv:2408.07532
-
Spatial Transformer Network YOLO Model for Agricultural Object Detection 31 Jul 2024 · 1 repository · arXiv:2407.21652
-
Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning 22 Jul 2024 · 0 repositories · arXiv:2407.15815
-
X-Recon: Learning-based Patient-specific High-Resolution CT Reconstruction from Orthogonal X-Ray Images 22 Jul 2024 · 1 repository · arXiv:2407.15356
-
Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction 24 Jun 2024 · 1 repository · arXiv:2406.16992
-
Infinite 3D Landmarks: Improving Continuous 2D Facial Landmark Detection 30 May 2024 · 0 repositories · arXiv:2405.20117
-
Vision-Language Modeling with Regularized Spatial Transformer Networks for All Weather Crosswind Landing of Aircraft 9 May 2024 · 0 repositories · arXiv:2405.05574
-
Efficient and Scalable Chinese Vector Font Generation via Component Composition 10 Apr 2024 · 0 repositories · arXiv:2404.06779
-
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser 7 Mar 2024 · 1 repository · arXiv:2403.04444
-
The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models 13 Feb 2024 · 0 repositories · arXiv:2402.08320
-
Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retinal OCT Images with Full and Sparse Annotations 4 Dec 2023 · 1 repository · arXiv:2312.01726
-
MultiScale Spectral-Spatial Convolutional Transformer for Hyperspectral Image Classification 28 Oct 2023 · 0 repositories · arXiv:2310.18550
-
A Multi-Scale Spatial Transformer U-Net for Simultaneously Automatic Reorientation and Segmentation of 3D Nuclear Cardiac Images 16 Oct 2023 · 0 repositories · arXiv:2310.10095
-
Revisiting Data Augmentation for Rotational Invariance in Convolutional Neural Networks 12 Oct 2023 · 0 repositories · arXiv:2310.08429
-
UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation 25 Sep 2023 · 1 repository · arXiv:2309.14335
-
A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space 21 Sep 2023 · 1 repository
-
MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer 16 Sep 2023 · 1 repository · arXiv:2309.09067Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
Test-Time Compensated Representation Learning for Extreme Traffic Forecasting 16 Sep 2023 · 0 repositories · arXiv:2309.09074
-
Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos 12 Sep 2023 · 0 repositories · arXiv:2309.06285
-
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers 3 Sep 2023 · 1 repository · arXiv:2309.01270
-
Homography Estimation in Complex Topological Scenes 2 Aug 2023 · 0 repositories · arXiv:2308.01086
-
Entropy Transformer Networks: A Learning Approach via Tangent Bundle Data Manifold 24 Jul 2023 · 0 repositories · arXiv:2307.12517
-
Learning Dense Correspondences between Photos and Sketches 24 Jul 2023 · 0 repositories · arXiv:2307.12967
-
Unsupervised Deformable Image Registration for Respiratory Motion Compensation in Ultrasound Images 23 Jun 2023 · 0 repositories · arXiv:2306.13332
-
Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs) 12 Jun 2023 · 0 repositories · arXiv:2306.06934
-
Vista-Morph: Unsupervised Image Registration of Visible-Thermal Facial Pairs 10 Jun 2023 · 0 repositories · arXiv:2306.06505
-
Optimizing ViViT Training: Time and Memory Reduction for Action Recognition 7 Jun 2023 · 0 repositories · arXiv:2306.04822
-
Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks 30 May 2023 · 0 repositories · arXiv:2305.19130
-
Scalable handwritten text recognition system for lexicographic sources of under-resourced languages and alphabets 28 Mar 2023 · 0 repositories · arXiv:2303.16256
-
DG-Trans: Dual-level Graph Transformer for Spatiotemporal Incident Impact Prediction on Traffic Networks 21 Mar 2023 · 1 repository · arXiv:2303.12238
-
Read Pointer Meters in complex environments based on a Human-like Alignment and Recognition Algorithm 28 Feb 2023 · 2 repositories · arXiv:2302.14323
-
RMSim: Controlled Respiratory Motion Simulation on Static Patient Scans 26 Jan 2023 · 2 repositories · arXiv:2301.11422
-
Boosting Urban Traffic Speed Prediction via Integrating Implicit Spatial Correlations 25 Dec 2022 · 0 repositories · arXiv:2212.12932
-
Event-based Monocular Dense Depth Estimation with Recurrent Transformers 6 Dec 2022 · 0 repositories · arXiv:2212.02791
-
ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation 1 Dec 2022 · 0 repositories · arXiv:2212.00435
-
Adversarial and Random Transformations for Robust Domain Adaptation and Generalization 13 Nov 2022 · 0 repositories · arXiv:2211.06788
-
SizeGAN: Improving Size Representation in Clothing Catalogs 5 Nov 2022 · 0 repositories · arXiv:2211.02892
-
A Deep Moving-camera Background Model 16 Sep 2022 · 1 repository · arXiv:2209.07923Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples)
-
LRT: An Efficient Low-Light Restoration Transformer for Dark Light Field Images 6 Sep 2022 · 0 repositories · arXiv:2209.02197
-
Automatic reorientation by deep learning to generate short axis SPECT myocardial perfusion images 7 Aug 2022 · 0 repositories · arXiv:2208.03752
-
Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer 1 Aug 2022 · 0 repositories · arXiv:2208.01161
-
Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds 26 Jul 2022 · 0 repositories · arXiv:2207.12659
-
Compositional Mixture Representations for Vision and Text 13 Jun 2022 · 0 repositories · arXiv:2206.06404
-
ViT-BEVSeg: A Hierarchical Transformer Network for Monocular Birds-Eye-View Segmentation 31 May 2022 · 1 repository · arXiv:2205.15667
-
Unsupervised Difference Learning for Noisy Rigid Image Alignment 24 May 2022 · 0 repositories · arXiv:2205.11829
-
DeepPortraitDrawing: Generating Human Body Images from Freehand Sketches 4 May 2022 · 0 repositories · arXiv:2205.02070
-
Spatial Transformer Network on Skeleton-based Gait Recognition 8 Apr 2022 · 1 repository · arXiv:2204.03873
-
SALISA: Saliency-based Input Sampling for Efficient Video Object Detection 5 Apr 2022 · 0 repositories · arXiv:2204.02397
-
Towards Implicit Text-Guided 3D Shape Generation 28 Mar 2022 · 1 repository · arXiv:2203.14622
-
A high-precision underwater object detection based on joint self-supervised deblurring and improved spatial transformer network 9 Mar 2022 · 0 repositories · arXiv:2203.04822
-
Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retina OCT Images 4 Mar 2022 · 1 repository · arXiv:2203.02390
-
MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video 2 Mar 2022 · 1 repository · arXiv:2203.00859Syntology official (archive's flag): 4 ran · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 4 harvested samples) · 4 pointer-only (licence)
-
Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations 2 Mar 2022 · 2 repositories · arXiv:2203.01325Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Tempera: Spatial Transformer Feature Pyramid Network for Cardiac MRI Segmentation 1 Mar 2022 · 1 repository · arXiv:2203.00355
-
Voxelmorph++ Going beyond the cranial vault with keypoint supervision and multi-channel instance optimisation 28 Feb 2022 · 2 repositories · arXiv:2203.00046
-
Voxelmorph++ Going beyond the cranial vault with keypoint supervision and multi-channel instance optimisation 4 Feb 2022 · 0 repositories
-
HDhuman: High-quality Human Novel-view Rendering from Sparse Views 20 Jan 2022 · 0 repositories · arXiv:2201.08158
-
DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation 16 Dec 2021 · 1 repository · arXiv:2112.08775
-
SAC-GAN: Structure-Aware Image Composition 13 Dec 2021 · 1 repository · arXiv:2112.06596
-
GAN-Supervised Dense Visual Alignment 9 Dec 2021 · 1 repository · arXiv:2112.05143Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
Probabilistic Tracking with Deep Factors 2 Dec 2021 · 0 repositories · arXiv:2112.01609
-
Extracting Deformation-Aware Local Features by Learning to Deform 20 Nov 2021 · 1 repository · arXiv:2111.10617Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples)
-
Multimodal Emotion Recognition on RAVDESS Dataset Using Transfer Learning 18 Nov 2021 · 0 repositories
-
It's About Time: Analog Clock Reading in the Wild 17 Nov 2021 · 0 repositories · arXiv:2111.09162
-
Symmetry-Aware Autoencoders: s-PCA and s-nlPCA 4 Nov 2021 · 1 repository · arXiv:2111.02893
-
Sparse Spatial Transformers for Few-Shot Learning 27 Sep 2021 · 1 repository · arXiv:2109.12932Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)
-
Spatial Transformer Networks for Curriculum Learning 22 Aug 2021 · 0 repositories · arXiv:2108.09696
-
Light Field Image Super-Resolution with Transformers 17 Aug 2021 · 1 repository · arXiv:2108.07597
-
heterogeneous temporal graph transformer: an intelligent system for evolving android malware detection 14 Aug 2021 · 1 repository
-
Automatic size and pose homogenization with spatial transformer network to improve and accelerate pediatric segmentation 6 Jul 2021 · 0 repositories · arXiv:2107.02655
-
Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imaging 23 Jun 2021 · 1 repository · arXiv:2106.12175
-
Content-Augmented Feature Pyramid Network with Light Linear Spatial Transformers for Object Detection 20 May 2021 · 0 repositories · arXiv:2105.09464
-
Using Adaptive Gradient for Texture Learning in Single-View 3D Reconstruction 29 Apr 2021 · 0 repositories · arXiv:2104.14169
-
Restoration of Video Frames from a Single Blurred Image with Motion Understanding 19 Apr 2021 · 0 repositories · arXiv:2104.09134
-
Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression 6 Apr 2021 · 2 repositories · arXiv:2104.02300Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples)
-
Transferable Model for Shape Optimization subject to Physical Constraints 19 Mar 2021 · 0 repositories · arXiv:2103.10805
-
Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers 16 Mar 2021 · 1 repository · arXiv:2103.09360
-
Pose Discrepancy Spatial Transformer Based Feature Disentangling for Partial Aspect Angles SAR Target Recognition 7 Mar 2021 · 0 repositories · arXiv:2103.04329
-
(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network 8 Feb 2021 · 0 repositories · arXiv:2102.04530
-
Diffeomorphic Spatial Transformer Networks 1 Jan 2021 · 0 repositories
-
PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers 27 Nov 2020 · 1 repository · arXiv:2011.13607
-
Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings 25 Nov 2020 · 1 repository · arXiv:2011.12589
-
Contralaterally Enhanced Networks for Thoracic Disease Detection 9 Oct 2020 · 0 repositories · arXiv:2010.04483
-
Spatial Transformer Point Convolution 3 Sep 2020 · 0 repositories · arXiv:2009.01427
-
VPC-Net: Completion of 3D Vehicles from MLS Point Clouds 8 Aug 2020 · 1 repository · arXiv:2008.03404
-
Deep Photo Cropper and Enhancer 3 Aug 2020 · 0 repositories · arXiv:2008.00634
-
Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images 3 Jul 2020 · 0 repositories · arXiv:2007.01464
-
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates 28 Jun 2020 · 1 repository · arXiv:2006.15480
Tasks archive 2025-07-28
20 shown of 200 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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