# Deep Space-Time Video Upsampling Networks

arXiv: https://arxiv.org/abs/2004.02432 · HTML: https://mlsanity.com/paper/2004.02432/

## Key facts

- Cited by 12 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 12 of 12)

- [XVFI: eXtreme Video Frame Interpolation](https://mlsanity.com/paper/2103.16206/) (2021)
- [DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting](https://mlsanity.com/paper/2111.09985/) (2021)
- [Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning](https://mlsanity.com/paper/2205.05264/) (2022)
- [Efficient Space-time Video Super Resolution using Low-Resolution Flow and Mask Upsampling](https://mlsanity.com/paper/2104.05778/) (2021)
- [MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2110.15327/) (2021)
- [Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution](https://mlsanity.com/paper/2310.17294/) (2023)
- [STDAN: Deformable Attention Network for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2203.06841/) (2022)
- [Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2104.07473/) (2021)
- [You Only Align Once: Bidirectional Interaction for Spatial-Temporal Video Super-Resolution](https://mlsanity.com/paper/2207.06345/) (2022)
- [Enhancing Space-time Video Super-resolution via Spatial-temporal Feature Interaction](https://mlsanity.com/paper/2207.08960/) (2022)
- [Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution](https://mlsanity.com/paper/2407.08466/) (2024)
- [Information Prebuilt Recurrent Reconstruction Network for Video Super-Resolution](https://mlsanity.com/paper/2112.05755/) (2021)

## Abstract (arXiv)

Video super-resolution (VSR) and frame interpolation (FI) are traditional computer vision problems, and the performance have been improving by incorporating deep learning recently. In this paper, we investigate the problem of jointly upsampling videos both in space and time, which is becoming more important with advances in display systems. One solution for this is to run VSR and FI, one by one, independently. This is highly inefficient as heavy deep neural networks (DNN) are involved in each solution. To this end, we propose an end-to-end DNN framework for the space-time video upsampling by efficiently merging VSR and FI into a joint framework. In our framework, a novel weighting scheme is proposed to fuse input frames effectively without explicit motion compensation for efficient processing of videos. The results show better results both quantitatively and qualitatively, while reducing the computation time (x7 faster) and the number of parameters (30%) compared to baselines.