Papers › Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation
Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation
Matteo Fabbri, Fabio Lanzi, Simone Calderara, Stefano Alletto, Rita Cucchiara
In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective compression method to drastically reduce the size of this representation. At the core of the proposed method lies our Volumetric Heatmap Autoencoder, a fully-convolutional network tasked with the compression of ground-truth heatmaps into a dense intermediate representation. A second model, the Code Predictor, is then trained to predict these codes, which can be decompressed at test time to re-obtain the original representation. Our experimental evaluation shows that our method performs favorably when compared to state of the art on both multi-person and single-person 3D human pose estimation datasets and, thanks to our novel compression strategy, can process full-HD images at the constant runtime of 8 fps regardless of the number of subjects in the scene. Code and models available at https://github.com/fabbrimatteo/LoCO .
In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | Human3.6M | LoCO | Average MPJPE (mm) | 51.1 | #71 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | LoCO | Multi-View or Monocular | Monocular | #71 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | LoCO | PA-MPJPE | 43.4 | #71 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | LoCO | Using 2D ground-truth joints | No | #71 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Panoptic | LoCO | Average MPJPE (mm) | 69 | #6 of 9 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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