# iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks

arXiv: https://arxiv.org/abs/2006.11161 · HTML: https://mlsanity.com/paper/2006.11161/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [INR-V: A Continuous Representation Space for Video-based Generative Tasks](https://mlsanity.com/paper/2210.16579/) (2022)
- [FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment](https://mlsanity.com/paper/2301.07330/) (2023)
- [Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric](https://mlsanity.com/paper/2203.08923/) (2022)
- [Can No-Reference Quality-Assessment Methods Serve as Perceptual Losses for Super-Resolution?](https://mlsanity.com/paper/2405.20392/) (2024)
- [Video super-resolution for single-photon LIDAR](https://mlsanity.com/paper/2210.10474/) (2022)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [Zoom, Enhance! Measuring Surveillance GAN Up-sampling](https://mlsanity.com/paper/2108.09285/) (2021)
- [Combining Contrastive and Supervised Learning for Video Super-Resolution Detection](https://mlsanity.com/paper/2205.10406/) (2022)
- [Global Stress Generation and Spatiotemporal Super-Resolution Physics-Informed Operator under Dynamic Loading for Two-Phase Random Materials](https://mlsanity.com/paper/2505.01438/) (2025)

## Abstract (arXiv)

Recently, learning-based models have enhanced the performance of single-image super-resolution (SISR). However, applying SISR successively to each video frame leads to a lack of temporal coherency. Convolutional neural networks (CNNs) outperform traditional approaches in terms of image quality metrics such as peak signal to noise ratio (PSNR) and structural similarity (SSIM). However, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors. We present iSeeBetter, a novel GAN-based spatio-temporal approach to video super-resolution (VSR) that renders temporally consistent super-resolution videos. iSeeBetter extracts spatial and temporal information from the current and neighboring frames using the concept of recurrent back-projection networks as its generator. Furthermore, to improve the "naturality" of the super-resolved image while eliminating artifacts seen with traditional algorithms, we utilize the discriminator from super-resolution generative adversarial network (SRGAN). Although mean squared error (MSE) as a primary loss-minimization objective improves PSNR/SSIM, these metrics may not capture fine details in the image resulting in misrepresentation of perceptual quality. To address this, we use a four-fold (MSE, perceptual, adversarial, and total-variation (TV)) loss function. Our results demonstrate that iSeeBetter offers superior VSR fidelity and surpasses state-of-the-art performance.