# HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model

arXiv: https://arxiv.org/abs/2204.05007 · HTML: https://mlsanity.com/paper/2204.05007/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 47 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://mlsanity.com/paper/2003.01251/) (2020)
- [PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing](https://mlsanity.com/paper/1805.04409/) (2018)
- [Learning Joint Spatial-Temporal Transformations for Video Inpainting](https://mlsanity.com/paper/2007.10247/) (2020)
- [Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries](https://mlsanity.com/paper/1803.08673/) (2018)
- [HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation](https://mlsanity.com/paper/1901.03861/) (2019)
- [HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features](https://mlsanity.com/paper/2011.11498/) (2020)
- [OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas](https://mlsanity.com/paper/1807.09620/) (2018)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [HarDNet: A Low Memory Traffic Network](https://mlsanity.com/paper/1909.00948/) (2019)
- [Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation](https://mlsanity.com/paper/2104.08771/) (2021)
- [DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama](https://mlsanity.com/paper/1811.11977/) (2018)
- [Spherical View Synthesis for Self-Supervised 360 Depth Estimation](https://mlsanity.com/paper/1909.08112/) (2019)
- [Self-Supervised Learning of Depth and Camera Motion from 360deg Videos](https://mlsanity.com/paper/1811.05304/) (2018)
- [Pano3D: A Holistic Benchmark and a Solid Baseline for 360o Depth Estimation](https://mlsanity.com/paper/2109.02749/) (2021)
- [Looking at the right stuff: Guided semantic-gaze for autonomous driving](https://mlsanity.com/paper/1911.10455/) (2019)
- [Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network](https://mlsanity.com/paper/1907.00939/) (2019)
- [Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning](https://mlsanity.com/paper/2109.10563/) (2021)
- [ODE-CNN: Omnidirectional Depth Extension Networks](https://mlsanity.com/paper/2007.01475/) (2020)
- [Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods](https://mlsanity.com/paper/1910.04099/) (2019)
- [J-MOD2: Joint Monocular Obstacle Detection and Depth Estimation](https://mlsanity.com/paper/1709.08480/) (2017)
- [PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation](https://mlsanity.com/paper/2202.01323/) (2022)

## Built on by (most cited first, 6 of 6)

- [Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation](https://mlsanity.com/paper/2406.12849/) (2024)
- [Event-based Monocular Dense Depth Estimation with Recurrent Transformers](https://mlsanity.com/paper/2212.02791/) (2022)
- [Omni2: Unifying Omnidirectional Image Generation and Editing in an Omni Model](https://mlsanity.com/paper/2504.11379/) (2025)
- [RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization](https://mlsanity.com/paper/2509.23991/) (2025)
- [SHIRE: Enhancing Sample Efficiency using Human Intuition in REinforcement Learning](https://mlsanity.com/paper/2409.09990/) (2024)
- [SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion](https://mlsanity.com/paper/2502.05859/) (2025)

## Abstract (arXiv)

Monocular omnidirectional depth estimation is receiving considerable research attention due to its broad applications for sensing 360deg surroundings. Existing approaches in this field suffer from limitations in recovering small object details and data lost during the ground-truth depth map acquisition. In this paper, a novel monocular omnidirectional depth estimation model, namely HiMODE is proposed based on a hybrid CNN+Transformer (encoder-decoder) architecture whose modules are efficiently designed to mitigate distortion and computational cost, without performance degradation. Firstly, we design a feature pyramid network based on the HNet block to extract high-resolution features near the edges. The performance is further improved, benefiting from a self and cross attention layer and spatial/temporal patches in the Transformer encoder and decoder, respectively. Besides, a spatial residual block is employed to reduce the number of parameters. By jointly passing the deep features extracted from an input image at each backbone block, along with the raw depth maps predicted by the transformer encoder-decoder, through a context adjustment layer, our model can produce resulting depth maps with better visual quality than the ground-truth. Comprehensive ablation studies demonstrate the significance of each individual module. Extensive experiments conducted on three datasets; Stanford3D, Matterport3D, and SunCG, demonstrate that HiMODE can achieve state-of-the-art performance for 360deg monocular depth estimation.