# Zoom in to the details of human-centric videos

arXiv: https://arxiv.org/abs/2005.13222 · HTML: https://mlsanity.com/paper/2005.13222/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 4 of 4)

- [Cross-Camera Human Motion Transfer by Time Series Analysis](https://mlsanity.com/paper/2109.14174/) (2021)
- [HighlightMe: Detecting Highlights from Human-Centric Videos](https://mlsanity.com/paper/2110.01774/) (2021)
- [Cross-Camera Deep Colorization](https://mlsanity.com/paper/2209.01211/) (2022)
- [Improving Video Colorization by Test-Time Tuning](https://mlsanity.com/paper/2307.11757/) (2023)

## Abstract (arXiv)

Presenting high-resolution (HR) human appearance is always critical for the human-centric videos. However, current imagery equipment can hardly capture HR details all the time. Existing super-resolution algorithms barely mitigate the problem by only considering universal and low-level priors of im-age patches. In contrast, our algorithm is under bias towards the human body super-resolution by taking advantage of high-level prior defined by HR human appearance. Firstly, a motion analysis module extracts inherent motion pattern from the HR reference video to refine the pose estimation of the low-resolution (LR) sequence. Furthermore, a human body reconstruction module maps the HR texture in the reference frames onto a 3D mesh model. Consequently, the input LR videos get super-resolved HR human sequences are generated conditioned on the original LR videos as well as few HR reference frames. Experiments on an existing dataset and real-world data captured by hybrid cameras show that our approach generates superior visual quality of human body compared with the traditional method.