A simple yet effective baseline for 3d human pose estimation

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract

Results from the Paper


 Ranked #1 on Monocular 3D Human Pose Estimation on Human3.6M (Use Video Sequence metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M SIM (SH detections) (MA) Average MPJPE (mm) 67.5 # 224
Monocular 3D Human Pose Estimation Human3.6M Martinez et. al. Use Video Sequence No # 1
Frames Needed 1 # 1
Need Ground Truth 2D Pose No # 1
Monocular 3D Human Pose Estimation Human3.6M SIM (SH detections FT) (MA) Average MPJPE (mm) 62.9 # 22
3D Human Pose Estimation Human3.6M SIM (SH detections FT) (MA) Average MPJPE (mm) 62.9 # 214
Using 2D ground-truth joints No # 1
Multi-View or Monocular Monocular # 1
3D Human Pose Estimation Human3.6M SIM (GT detections) (MA) Average MPJPE (mm) 45.5 # 94
Using 2D ground-truth joints Yes # 1
3D Human Pose Estimation HumanEva-I SIM (SH detections) Mean Reconstruction Error (mm) 24.6 # 16

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
3D Human Pose Estimation 3DPW Simple-baseline PA-MPJPE 157.0 # 76

Methods


No methods listed for this paper. Add relevant methods here