# SweepNet: Wide-baseline Omnidirectional Depth Estimation

arXiv: https://arxiv.org/abs/1902.10904 · HTML: https://mlsanity.com/paper/1902.10904/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2019.

## Built on by (most cited first, 24 of 24)

- [Deep Learning for Omnidirectional Vision: A Survey and New Perspectives](https://mlsanity.com/paper/2205.10468/) (2022)
- [3D Scene Geometry Estimation from 360^circ Imagery: A Survey](https://mlsanity.com/paper/2401.09252/) (2024)
- [PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation](https://mlsanity.com/paper/2202.01323/) (2022)
- [Unsupervised OmniMVS: Efficient Omnidirectional Depth Inference via Establishing Pseudo-Stereo Supervision](https://mlsanity.com/paper/2302.09922/) (2023)
- [RomniStereo: Recurrent Omnidirectional Stereo Matching](https://mlsanity.com/paper/2401.04345/) (2024)
- [FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization](https://mlsanity.com/paper/2401.13786/) (2024)
- [Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation](https://mlsanity.com/paper/2411.18335/) (2024)
- [OmniSyn: Synthesizing 360 Videos with Wide-baseline Panoramas](https://mlsanity.com/paper/2202.08752/) (2022)
- [SDGE: Stereo Guided Depth Estimation for 360^circ Camera Sets](https://mlsanity.com/paper/2402.11791/) (2024)
- [OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos](https://mlsanity.com/paper/2404.00676/) (2024)
- [Depth360: Self-supervised Learning for Monocular Depth Estimation using Learnable Camera Distortion Model](https://mlsanity.com/paper/2110.10415/) (2021)
- [TSDF-Sampling: Efficient Sampling for Neural Surface Field using Truncated Signed Distance Field](https://mlsanity.com/paper/2311.17878/) (2023)
- [Geometry-Informed Distance Candidate Selection for Adaptive Lightweight Omnidirectional Stereo Vision with Fisheye Images](https://mlsanity.com/paper/2405.05355/) (2024)
- [FastViDAR: Real-Time Omnidirectional Depth Estimation via Alternative Hierarchical Attention](https://mlsanity.com/paper/2509.23733/) (2025)
- [MSI-NeRF: Linking Omni-Depth with View Synthesis through Multi-Sphere Image aided Generalizable Neural Radiance Field](https://mlsanity.com/paper/2403.10840/) (2024)
- [Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Model](https://mlsanity.com/paper/2503.23502/) (2025)
- [Exploring Surround-View Fisheye Camera 3D Object Detection](https://mlsanity.com/paper/2511.18695/) (2025)
- [Depth Estimation Analysis of Orthogonally Divergent Fisheye Cameras with Distortion Removal](https://mlsanity.com/paper/2307.03602/) (2023)
- [MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas](https://mlsanity.com/paper/2408.01653/) (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)
- [Robust and Flexible Omnidirectional Depth Estimation with Multiple 360-degree Cameras](https://mlsanity.com/paper/2409.14766/) (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)

## Abstract (arXiv)

Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions. In this paper, we propose a novel wide-baseline omnidirectional stereo algorithm which computes the dense depth estimate from the fisheye images using a deep convolutional neural network. The capture system consists of multiple cameras mounted on a wide-baseline rig with ultrawide field of view (FOV) lenses, and we present the calibration algorithm for the extrinsic parameters based on the bundle adjustment. Instead of estimating depth maps from multiple sets of rectified images and stitching them, our approach directly generates one dense omnidirectional depth map with full 360-degree coverage at the rig global coordinate system. To this end, the proposed neural network is designed to output the cost volume from the warped images in the sphere sweeping method, and the final depth map is estimated by taking the minimum cost indices of the aggregated cost volume by SGM. For training the deep neural network and testing the entire system, realistic synthetic urban datasets are rendered using Blender. The experiments using the synthetic and real-world datasets show that our algorithm outperforms the conventional depth estimation methods and generate highly accurate depth maps.