Putting People in their Place: Monocular Regression of 3D People in Depth

CVPR 2022  ·  Yu Sun, Wu Liu, Qian Bao, Yili Fu, Tao Mei, Michael J. Black ·

Given an image with multiple people, our goal is to directly regress the pose and shape of all the people as well as their relative depth. Inferring the depth of a person in an image, however, is fundamentally ambiguous without knowing their height. This is particularly problematic when the scene contains people of very different sizes, e.g. from infants to adults. To solve this, we need several things. First, we develop a novel method to infer the poses and depth of multiple people in a single image. While previous work that estimates multiple people does so by reasoning in the image plane, our method, called BEV, adds an additional imaginary Bird's-Eye-View representation to explicitly reason about depth. BEV reasons simultaneously about body centers in the image and in depth and, by combing these, estimates 3D body position. Unlike prior work, BEV is a single-shot method that is end-to-end differentiable. Second, height varies with age, making it impossible to resolve depth without also estimating the age of people in the image. To do so, we exploit a 3D body model space that lets BEV infer shapes from infants to adults. Third, to train BEV, we need a new dataset. Specifically, we create a "Relative Human" (RH) dataset that includes age labels and relative depth relationships between the people in the images. Extensive experiments on RH and AGORA demonstrate the effectiveness of the model and training scheme. BEV outperforms existing methods on depth reasoning, child shape estimation, and robustness to occlusion. The code and dataset are released for research purposes.

PDF Abstract CVPR 2022 PDF CVPR 2022 Abstract

Results from the Paper

 Ranked #1 on 3D Depth Estimation on Relative Human (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
3D Depth Estimation Relative Human BEV PCDR 68.27 # 1
PCDR-Baby 60.77 # 1
PCDR-Kid 67.09 # 1
PCDR-Teen 66.07 # 1
PCDR-Adult 69.71 # 1
mPCDK 0.884 # 1


No methods listed for this paper. Add relevant methods here