Papers › Human Body Model Fitting by Learned Gradient Descent
Human Body Model Fitting by Learned Gradient Descent
Jie Song, Xu Chen, Otmar Hilliges
We propose a novel algorithm for the fitting of 3D human shape to images. Combining the accuracy and refinement capabilities of iterative gradient-based optimization techniques with the robustness of deep neural networks, we propose a gradient descent algorithm that leverages a neural network to predict the parameter update rule for each iteration. This per-parameter and state-aware update guides the optimizer towards a good solution in very few steps, converging in typically few steps. During training our approach only requires MoCap data of human poses, parametrized via SMPL. From this data the network learns a subspace of valid poses and shapes in which optimization is performed much more efficiently. The approach does not require any hard to acquire image-to-3D correspondences. At test time we only optimize the 2D joint re-projection error without the need for any further priors or regularization terms. We show empirically that this algorithm is fast (avg. 120ms convergence), robust to initialization and dataset, and achieves state-of-the-art results on public evaluation datasets including the challenging 3DPW in-the-wild benchmark (improvement over SMPLify 45%) and also approaches using image-to-3D correspondences
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
2 archive task tags without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | EMDB | LGD | Average MPJAE (deg) | 25.1572 | #12 of 13 | Archive leaderboard | report |
| 3D Human Pose Estimation | EMDB | LGD | Average MPJAE-PA (deg) | 25.6425 | #12 of 13 | Archive leaderboard | report |
| 3D Human Pose Estimation | EMDB | LGD | Average MPJPE (mm) | 115.82 | #12 of 13 | Archive leaderboard | report |
| 3D Human Pose Estimation | EMDB | LGD | Average MPJPE-PA (mm) | 81.1389 | #12 of 13 | Archive leaderboard | report |
| 3D Human Pose Estimation | EMDB | LGD | Average MVE (mm) | 140.63 | #12 of 13 | Archive leaderboard | report |
| 3D Human Pose Estimation | EMDB | LGD | Average MVE-PA (mm) | 95.7255 | #12 of 13 | Archive leaderboard | report |
| 3D Human Pose Estimation | EMDB | LGD | Jitter (10m/s^3) | 72.9695 | #12 of 13 | 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.
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