# ODE-CNN: Omnidirectional Depth Extension Networks

arXiv: https://arxiv.org/abs/2007.01475 · HTML: https://mlsanity.com/paper/2007.01475/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2020.

## Built on by (most cited first, 18 of 18)

- [PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation](https://mlsanity.com/paper/2203.09283/) (2022)
- [Dynamic Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2202.09769/) (2022)
- [OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion](https://mlsanity.com/paper/2203.00838/) (2022)
- [ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation](https://mlsanity.com/paper/2112.14440/) (2021)
- [Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation](https://mlsanity.com/paper/2109.02749/) (2021)
- [HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions](https://mlsanity.com/paper/2303.11616/) (2023)
- [Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion](https://mlsanity.com/paper/2403.16376/) (2024)
- [PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation](https://mlsanity.com/paper/2202.01323/) (2022)
- [HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model](https://mlsanity.com/paper/2204.05007/) (2022)
- [Revisiting 360 Depth Estimation with PanoGabor: A New Fusion Perspective](https://mlsanity.com/paper/2408.16227/) (2024)
- [Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration](https://mlsanity.com/paper/2408.09336/) (2024)
- [Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes](https://mlsanity.com/paper/2108.08076/) (2021)
- [SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion](https://mlsanity.com/paper/2502.05859/) (2025)
- [Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding](https://mlsanity.com/paper/2212.05040/) (2022)
- [MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas](https://mlsanity.com/paper/2408.01653/) (2024)
- [Robust and Flexible Omnidirectional Depth Estimation with Multiple 360-degree Cameras](https://mlsanity.com/paper/2409.14766/) (2024)
- [PAGCNet: A Pose-Aware and Geometry Constrained Framework for Panoramic Depth Estimation](https://mlsanity.com/paper/2510.07817/) (2025)
- [Cross360: 360deg Monocular Depth Estimation via Cross Projections Across Scales](https://mlsanity.com/paper/2601.17271/) (2026)

## Abstract (arXiv)

Omnidirectional 360deg camera proliferates rapidly for autonomous robots since it significantly enhances the perception ability by widening the field of view(FoV). However, corresponding 360deg depth sensors, which are also critical for the perception system, are still difficult or expensive to have. In this paper, we propose a low-cost 3D sensing system that combines an omnidirectional camera with a calibrated projective depth camera, where the depth from the limited FoV can be automatically extended to the rest of the recorded omnidirectional image. To accurately recover the missing depths, we design an omnidirectional depth extension convolutional neural network(ODE-CNN), in which a spherical feature transform layer(SFTL) is embedded at the end of feature encoding layers, and a deformable convolutional spatial propagation network(D-CSPN) is appended at the end of feature decoding layers. The former resamples the neighborhood of each pixel in the omnidirectional coordination to the projective coordination, which reduces the difficulty of feature learning, and the later automatically finds a proper context to well align the structures in the estimated depths via CNN w.r.t. the reference image, which significantly improves the visual quality. Finally, we demonstrate the effectiveness of proposed ODE-CNN over the popular 360D dataset and show that ODE-CNN significantly outperforms (relatively 33% reduction in-depth error) other state-of-the-art (SoTA) methods.