# RomniStereo: Recurrent Omnidirectional Stereo Matching

arXiv: https://arxiv.org/abs/2401.04345 · HTML: https://mlsanity.com/paper/2401.04345/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 9 Jan 2024.

## Builds on (most cited first, 18 of 18)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas](https://mlsanity.com/paper/1807.09620/) (2018)
- [UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimation](https://mlsanity.com/paper/2102.03550/) (2021)
- [CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow](https://mlsanity.com/paper/2203.16896/) (2022)
- [OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion](https://mlsanity.com/paper/2203.00838/) (2022)
- [360SD-Net: 360deg Stereo Depth Estimation with Learnable Cost Volume](https://mlsanity.com/paper/1911.04460/) (2019)
- [Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching](https://mlsanity.com/paper/2307.14071/) (2023)
- [Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360deg Panoramic Imagery](https://mlsanity.com/paper/1808.06253/) (2018)
- [SweepNet: Wide-baseline Omnidirectional Depth Estimation](https://mlsanity.com/paper/1902.10904/) (2019)
- [OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching](https://mlsanity.com/paper/1908.06257/) (2019)
- [360^circ Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of Icosahedron](https://mlsanity.com/paper/2007.06891/) (2020)
- [An Improved RaftStereo Trained with A Mixed Dataset for the Robust Vision Challenge 2022](https://mlsanity.com/paper/2210.12785/) (2022)

## Built on by (most cited first, 8 of 8)

- [FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera](https://mlsanity.com/paper/2409.15054/) (2024)
- [Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model](https://mlsanity.com/paper/2503.23502/) (2025)
- [A Flexible Recursive Network for Video Stereo Matching Based on Residual Estimation](https://mlsanity.com/paper/2406.03333/) (2024)
- [Real-time Multi-view Omnidirectional Depth Estimation for Real Scenarios based on Teacher-Student Learning with Unlabeled Data](https://mlsanity.com/paper/2409.07843/) (2024)
- [Reference-Free Omnidirectional Stereo Matching via Multi-View Consistency Maximization](https://mlsanity.com/paper/2603.15019/) (2026)
- [H-OmniStereo: Zero-Shot Omnidirectional Stereo Matching with Heading-Aligned Normal Priors](https://mlsanity.com/paper/2605.14963/) (2026)
- [OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras](https://mlsanity.com/paper/2607.03038/) (2026)
- [Revisiting Matching Response and Swept Feature Volumes for Wide-baseline Omnidirectional Stereo](https://mlsanity.com/paper/2607.11097/) (2026)

## Abstract (arXiv)

Omnidirectional stereo matching (OSM) is an essential and reliable means for 360circ depth sensing. However, following earlier works on conventional stereo matching, prior state-of-the-art (SOTA) methods rely on a 3D encoder-decoder block to regularize the cost volume, causing the whole system complicated and sub-optimal results. Recently, the Recurrent All-pairs Field Transforms (RAFT) based approach employs the recurrent update in 2D and has efficiently improved image-matching tasks, ie, optical flow, and stereo matching. To bridge the gap between OSM and RAFT, we mainly propose an opposite adaptive weighting scheme to seamlessly transform the outputs of spherical sweeping of OSM into the required inputs for the recurrent update, thus creating a recurrent omnidirectional stereo matching (RomniStereo) algorithm. Furthermore, we introduce two techniques, ie, grid embedding and adaptive context feature generation, which also contribute to RomniStereo's performance. Our best model improves the average MAE metric by 40.7% over the previous SOTA baseline across five datasets. When visualizing the results, our models demonstrate clear advantages on both synthetic and realistic examples. The code is available at urlhttps://github.com/HalleyJiang/RomniStereo.