Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation

11 Oct 2021  ·  Hui Shuai, Lele Wu, Qingshan Liu ·

This paper proposes a unified framework dubbed Multi-view and Temporal Fusing Transformer (MTF-Transformer) to adaptively handle varying view numbers and video length without camera calibration in 3D Human Pose Estimation (HPE). It consists of Feature Extractor, Multi-view Fusing Transformer (MFT), and Temporal Fusing Transformer (TFT). Feature Extractor estimates 2D pose from each image and fuses the prediction according to the confidence. It provides pose-focused feature embedding and makes subsequent modules computationally lightweight. MFT fuses the features of a varying number of views with a novel Relative-Attention block. It adaptively measures the implicit relative relationship between each pair of views and reconstructs more informative features. TFT aggregates the features of the whole sequence and predicts 3D pose via a transformer. It adaptively deals with the video of arbitrary length and fully unitizes the temporal information. The migration of transformers enables our model to learn spatial geometry better and preserve robustness for varying application scenarios. We report quantitative and qualitative results on the Human3.6M, TotalCapture, and KTH Multiview Football II. Compared with state-of-the-art methods with camera parameters, MTF-Transformer obtains competitive results and generalizes well to dynamic capture with an arbitrary number of unseen views.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M MTF-Transformer (M=0.4, T=1, N=1) Average MPJPE (mm) 50.7 # 174
Using 2D ground-truth joints No # 2
Multi-View or Monocular Monocular # 1
3D Human Pose Estimation Human3.6M MTF-Transformer (M=0.4, T=7, N=1) Average MPJPE (mm) 49.4 # 154
Using 2D ground-truth joints No # 2
Multi-View or Monocular Monocular # 1
3D Human Pose Estimation Human3.6M MTF-Transformer (M=0.4, T=1) Average MPJPE (mm) 29.4 # 29
Using 2D ground-truth joints No # 2
Multi-View or Monocular Multi-View # 1
3D Human Pose Estimation Human3.6M MTF-Transformer (M=0.4, T=7) Average MPJPE (mm) 28.5 # 25
Using 2D ground-truth joints No # 2
Multi-View or Monocular Multi-View # 1
3D Human Pose Estimation Total Capture MTF-Transformer (M=0.4, T=7) Average MPJPE (mm) 29.2 # 7

Methods