MIPNet: Multi-Instance Pose Networks

1Carnegie Mellon University, 2Amazon
Interpolate start reference image.

Input Image

Interpolate start reference image.

Top-Down Pose Estimator

Interpolation end reference image.

MIPNet

Abstract

A key assumption of top-down human pose estimation approaches is their expectation of having a single person/instance present in the input bounding box. This often leads to failures in crowded scenes with occlusions. We propose a novel solution to overcome the limitations of this fundamental assumption. Our Multi-Instance Pose Network (MIPNet) allows for predicting multiple 2D pose instances within a given bounding box. We introduce a Multi-Instance Modulation Block (MIMB) that can adaptively modulate channel-wise feature responses for each instance and is parameter efficient.

We demonstrate the efficacy of our approach by evaluating on COCO, CrowdPose, and OCHuman datasets. Specifically, we achieve 70.0 AP on CrowdPose and 42.5 AP on OCHuman test sets, a significant improvement of 2.4 AP and 6.5 AP over the prior art, respectively. When using ground truth bounding boxes for inference, MIPNet achieves an improvement of 0.7 AP on COCO, 0.9 AP on CrowdPose, and 9.1 AP on OCHuman validation sets compared to HRNet. Interestingly, when fewer, high confidence bounding boxes are used, HRNet's performance degrades (by 5 AP) on OCHuman, whereas MIPNet maintains a relatively stable performance (drop of 1 AP) for the same inputs.

Pose Estimation under Occlusion


Interpolate start reference image.

Input

Interpolate start reference image.

HRNet

Interpolation end reference image.

MIPNet

Interpolate start reference image.

Input

Interpolate start reference image.

HRNet

Interpolation end reference image.

MIPNet

Interpolate start reference image.

Input

Interpolate start reference image.

HRNet

Interpolation end reference image.

MIPNet

Interpolate start reference image.

Input

Interpolate start reference image.

HRNet

Interpolation end reference image.

MIPNet

Interpolate start reference image.

Input

Interpolate start reference image.

HRNet

Interpolation end reference image.

MIPNet

Interpolate start reference image.

Input

Interpolate start reference image.

HRNet

Interpolation end reference image.

MIPNet

BibTeX


      @InProceedings{Khirodkar_2021_ICCV,
              author    = {Khirodkar, Rawal and Chari, Visesh and Agrawal, Amit and Tyagi, Ambrish},
              title     = {Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation},
              booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
              month     = {October},
              year      = {2021},
              pages     = {3122-3131}
          }