# HSTR-Net: High Spatio-Temporal Resolution Video Generation For Wide Area Surveillance

arXiv: https://arxiv.org/abs/2204.04435 · HTML: https://mlsanity.com/paper/2204.04435/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 9 Apr 2022.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Detection and Tracking Meet Drones Challenge](https://mlsanity.com/paper/2001.06303/) (2020)
- [Depth-Aware Video Frame Interpolation](https://mlsanity.com/paper/1904.00830/) (2019)
- [Image Super-Resolution by Neural Texture Transfer](https://mlsanity.com/paper/1903.00834/) (2019)
- [CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping](https://mlsanity.com/paper/1807.10547/) (2018)
- [MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution](https://mlsanity.com/paper/2106.02299/) (2021)
- [Blurry Video Frame Interpolation](https://mlsanity.com/paper/2002.12259/) (2020)
- [A Dual Camera System for High Spatiotemporal Resolution Video Acquisition](https://mlsanity.com/paper/1909.13051/) (2019)

## Abstract (arXiv)

Wide area surveillance has many applications and tracking of objects under observation is an important task, which often needs high spatio-temporal resolution (HSTR) video for better precision. This paper presents the usage of multiple video feeds for the generation of HSTR video as an extension of reference based super resolution (RefSR). One feed captures video at high spatial resolution with low frame rate (HSLF) while the other captures low spatial resolution and high frame rate (LSHF) video simultaneously for the same scene. The main purpose is to create an HSTR video from the fusion of HSLF and LSHF videos. In this paper we propose an end-to-end trainable deep network that performs optical flow estimation and frame reconstruction by combining inputs from both video feeds. The proposed architecture provides significant improvement over existing video frame interpolation and RefSR techniques in terms of objective PSNR and SSIM metrics.