# CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability

arXiv: https://arxiv.org/abs/2202.00416 · HTML: https://mlsanity.com/paper/2202.00416/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 1 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Variable Rate Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06085/) (2015)
- [DSSLIC: Deep Semantic Segmentation-based Layered Image Compression](https://mlsanity.com/paper/1806.03348/) (2018)
- [Conditional Coding for Flexible Learned Video Compression](https://mlsanity.com/paper/2104.07930/) (2021)
- [Learning Binary Residual Representations for Domain-specific Video Streaming](https://mlsanity.com/paper/1712.05087/) (2017)
- [ViSTRA2: Video Coding using Spatial Resolution and Effective Bit Depth Adaptation](https://mlsanity.com/paper/1911.02833/) (2019)
- [Versatile video coding and super-resolution for efficient delivery of 8K video with 4K backward-compatibility](https://mlsanity.com/paper/2002.06922/) (2020)
- [Perceptually-inspired super-resolution of compressed videos](https://mlsanity.com/paper/2106.08147/) (2021)
- [Multitask Learning for VVC Quality Enhancement and Super-Resolution](https://mlsanity.com/paper/2104.08319/) (2021)

## Abstract (arXiv)

In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.