# Degradation-agnostic Correspondence from Resolution-asymmetric Stereo

arXiv: https://arxiv.org/abs/2204.01429 · HTML: https://mlsanity.com/paper/2204.01429/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 60 references that are in the map.
- First posted on arXiv 4 Apr 2022.

## Builds on (most cited first, 28 of 28)

- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [3D Photography using Context-aware Layered Depth Inpainting](https://mlsanity.com/paper/2004.04727/) (2020)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [To learn image super-resolution, use a GAN to learn how to do image degradation first](https://mlsanity.com/paper/1807.11458/) (2018)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Real-time self-adaptive deep stereo](https://mlsanity.com/paper/1810.05424/) (2018)
- [Synthetic Depth-of-Field with a Single-Camera Mobile Phone](https://mlsanity.com/paper/1806.04171/) (2018)
- [DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning](https://mlsanity.com/paper/2003.13446/) (2020)
- [What Do Neural Networks Learn When Trained With Random Labels?](https://mlsanity.com/paper/2006.10455/) (2020)
- [Camera Lens Super-Resolution](https://mlsanity.com/paper/1904.03378/) (2019)
- [Parallax Attention for Unsupervised Stereo Correspondence Learning](https://mlsanity.com/paper/2009.08250/) (2020)
- [Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation](https://mlsanity.com/paper/2008.07130/) (2020)
- [Dual-Camera Super-Resolution with Aligned Attention Modules](https://mlsanity.com/paper/2109.01349/) (2021)
- [Self-Supervised Learning for Stereo Matching with Self-Improving Ability](https://mlsanity.com/paper/1709.00930/) (2017)
- [StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching](https://mlsanity.com/paper/2005.01927/) (2020)
- [Real-world Person Re-Identification via Degradation Invariance Learning](https://mlsanity.com/paper/2004.04933/) (2020)
- [Unsupervised Cross-spectral Stereo Matching by Learning to Synthesize](https://mlsanity.com/paper/1903.01078/) (2019)
- [Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation](https://mlsanity.com/paper/1903.10427/) (2019)

## Built on by (most cited first, 5 of 5)

- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [Towards RGB-NIR Cross-modality Image Registration and Beyond](https://mlsanity.com/paper/2405.19914/) (2024)
- [Iterative Volume Fusion for Asymmetric Stereo Matching](https://mlsanity.com/paper/2508.09543/) (2025)
- [CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality](https://mlsanity.com/paper/2410.05735/) (2024)

## Abstract (arXiv)

In this paper, we study the problem of stereo matching from a pair of images with different resolutions, e.g., those acquired with a tele-wide camera system. Due to the difficulty of obtaining ground-truth disparity labels in diverse real-world systems, we start from an unsupervised learning perspective. However, resolution asymmetry caused by unknown degradations between two views hinders the effectiveness of the generally assumed photometric consistency. To overcome this challenge, we propose to impose the consistency between two views in a feature space instead of the image space, named feature-metric consistency. Interestingly, we find that, although a stereo matching network trained with the photometric loss is not optimal, its feature extractor can produce degradation-agnostic and matching-specific features. These features can then be utilized to formulate a feature-metric loss to avoid the photometric inconsistency. Moreover, we introduce a self-boosting strategy to optimize the feature extractor progressively, which further strengthens the feature-metric consistency. Experiments on both simulated datasets with various degradations and a self-collected real-world dataset validate the superior performance of the proposed method over existing solutions.