# StereoINR: Cross-View Geometry Consistent Stereo Super Resolution with Implicit Neural Representation

arXiv: https://arxiv.org/abs/2505.05509 · HTML: https://mlsanity.com/paper/2505.05509/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 48 references that are in the map.
- First posted on arXiv 7 May 2025.

## Builds on (most cited first, 24 of 24)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Interpreting Super-Resolution Networks with Local Attribution Maps](https://mlsanity.com/paper/2011.11036/) (2020)
- [Local Texture Estimator for Implicit Representation Function](https://mlsanity.com/paper/2111.08918/) (2021)
- [VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution](https://mlsanity.com/paper/2206.04647/) (2022)
- [NAFSSR: Stereo Image Super-Resolution Using NAFNet](https://mlsanity.com/paper/2204.08714/) (2022)
- [On Efficient Transformer-Based Image Pre-training for Low-Level Vision](https://mlsanity.com/paper/2112.10175/) (2021)
- [UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2103.12716/) (2021)
- [Learning Parallax Attention for Stereo Image Super-Resolution](https://mlsanity.com/paper/1903.05784/) (2019)
- [Cascaded Local Implicit Transformer for Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2303.16513/) (2023)
- [Implicit Transformer Network for Screen Content Image Continuous Super-Resolution](https://mlsanity.com/paper/2112.06174/) (2021)
- [Parallax Attention for Unsupervised Stereo Correspondence Learning](https://mlsanity.com/paper/2009.08250/) (2020)
- [Symmetric Parallax Attention for Stereo Image Super-Resolution](https://mlsanity.com/paper/2011.03802/) (2020)
- [Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution](https://mlsanity.com/paper/2007.05230/) (2020)
- [Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation](https://mlsanity.com/paper/2106.00985/) (2021)
- [Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors](https://mlsanity.com/paper/2407.09919/) (2024)
- [Parameter Efficient Local Implicit Image Function Network for Face Segmentation](https://mlsanity.com/paper/2303.15122/) (2023)
- [Perception-Oriented Stereo Image Super-Resolution](https://mlsanity.com/paper/2207.06617/) (2022)

## Built on by (most cited first, 3 of 3)

- [ViewBridge:Revisiting Cross-View Localization from Image Matching](https://mlsanity.com/paper/2508.10716/) (2025)
- [Implicit Neural Representations: A Signal Processing Perspective](https://mlsanity.com/paper/2604.15047/) (2026)
- [HIMOSA: Efficient Remote Sensing Image Super-Resolution with Hierarchical Mixture of Sparse Attention](https://mlsanity.com/paper/2512.00275/) (2025)

## Abstract (arXiv)

Stereo image super-resolution (SSR) aims to enhance high-resolution details by leveraging information from stereo image pairs. However, existing stereo super-resolution (SSR) upsampling methods (e.g., pixel shuffle) often overlook cross-view geometric consistency and are limited to fixed-scale upsampling. The key issue is that previous upsampling methods use convolution to independently process deep features of different views, lacking cross-view and non-local information perception, making it difficult to select beneficial information from multi-view scenes adaptively. In this work, we propose Stereo Implicit Neural Representation (StereoINR), which innovatively models stereo image pairs as continuous implicit representations. This continuous representation breaks through the scale limitations, providing a unified solution for arbitrary-scale stereo super-resolution reconstruction of left-right views. Furthermore, by incorporating spatial warping and cross-attention mechanisms, StereoINR enables effective cross-view information fusion and achieves significant improvements in pixel-level geometric consistency. Extensive experiments across multiple datasets show that StereoINR outperforms out-of-training-distribution scale upsampling and matches state-of-the-art SSR methods within training-distribution scales.