</> Code with Papers by Syntology

Methods › Computer Vision › Image Model Blocks › Hourglass Module

Hourglass Module

31 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

An Hourglass Module is an image block module used mainly for pose estimation tasks. The design of the hourglass is motivated by the need to capture information at every scale. While local evidence is essential for identifying features like faces and hands, a final pose estimate requires a coherent understanding of the full body. The person’s orientation, the arrangement of their limbs, and the relationships of adjacent joints are among the many cues that are best recognized at different scales in the image. The hourglass is a simple, minimal design that has the capacity to capture all of these features and bring them together to output pixel-wise predictions.

The network must have some mechanism to effectively process and consolidate features across scales. The Hourglass uses a single pipeline with skip layers to preserve spatial information at each resolution. The network reaches its lowest resolution at 4x4 pixels allowing smaller spatial filters to be applied that compare features across the entire space of the image.

The hourglass is set up as follows: Convolutional and max pooling layers are used to process features down to a very low resolution. At each max pooling step, the network branches off and applies more convolutions at the original pre-pooled resolution. After reaching the lowest resolution, the network begins the top-down sequence of upsampling and combination of features across scales. To bring together information across two adjacent resolutions, we do nearest neighbor upsampling of the lower resolution followed by an elementwise addition of the two sets of features. The topology of the hourglass is symmetric, so for every layer present on the way down there is a corresponding layer going up.

After reaching the output resolution of the network, two consecutive rounds of 1x1 convolutions are applied to produce the final network predictions. The output of the network is a set of heatmaps where for a given heatmap the network predicts the probability of a joint’s presence at each and every pixel.

Source: Stacked Hourglass Networks for Human Pose EstimationSee Code · bearpaw/pytorch-pose

Papers archive 2025-07-28

30 shown of 31, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 49 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Pose Estimation10
Object9
Object Detection9
object-detection9
Multi-Task Learning3
3D Pose Estimation2
Decoder2
Face Alignment2
Multi-Person Pose Estimation2
Segmentation2
Semantic Segmentation2
Stereo Matching2
Stereo Matching Hand2
2D Human Pose Estimation1
2D Pose Estimation1
3D Human Pose Estimation1
3D Multi-Person Human Pose Estimation1
3D Multi-Person Pose Estimation1
3D Volumetric Reconstruction1
Automatic Speech Recognition1

Usage over time archive 2025-07-28

Papers per year tagged with Hourglass Module: 2016 to 2024, peak 10 10 0 2016: 1 paper 2016 2017: 0 papers 2017 2018: 2 papers 2018 2019: 10 papers 2019 2020: 9 papers 2020 2021: 6 papers 2021 2022: 1 paper 2022 2023: 1 paper 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (31 dated). Bars are counts, not a trend claim.

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

Image Model Blocks

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