Fundamental Research 2023

MILI: Multi-person Inference from a Low-resolution Image

 

Kun Li1,* Yunke Liu1, Yu-Kun Lai2, Jingyu Yang1,*

1 Tianjin University   2 Cardiff University  

  * Corresponding author

 

[Paper] [Code]

 

Abstract

Existing multi-person reconstruction methods require the human bodies in the input image to occupy a considerable portion of the picture. However, low-resolution human objects are ubiquitous due to trade-off between the field of view and target distance given a limited camera resolution. In this paper, we propose an end-to-end multi-task framework for multi-person inference from a low-resolution image (MILI). To perceive more information from a low-resolution image, we use pair-wise images at high resolution and low resolution for training, and design a restoration network with a simple loss for better feature extraction from the low-resolution image. To address the occlusion problem in multi-person scenes, we propose an occlusion-aware mask prediction network to estimate the mask of each person during 3D mesh regression. Experimental results on both small-scale scenes and large-scale scenes demonstrate that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.


Method

 

 

Fig 1. Overview of the proposed MILI.

 

 

Fig 2. The details of the restoration network.

 


Results (PANDA)

 

 


Results (COCO and MuPoTS-3D)

 

 


Technical Paper

 


Citation

Kun Li, Yunke Liu, Yu-Kun Lai, Jingyu Yang. "MILI: Multi-person Inference from a Low-resolution Image". Fundamental Research, 2023.

 

@article{MILI,
  author = {Kun Li and Yunke Liu and Yu-Kun Lai and Jingyu Yang},
  title = {MILI: Multi-person Inference from a Low-resolution Image},
  booktitle = {Fundamental Research},
  year={2023},
}