# GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation

arXiv: https://arxiv.org/abs/2302.09884 · HTML: https://mlsanity.com/paper/2302.09884/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images](https://mlsanity.com/paper/1808.08114/) (2018)
- [TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation](https://mlsanity.com/paper/2102.08005/) (2021)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints](https://mlsanity.com/paper/1802.05522/) (2018)
- [CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction](https://mlsanity.com/paper/1704.03489/) (2017)
- [Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation](https://mlsanity.com/paper/1906.03525/) (2019)
- [Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume](https://mlsanity.com/paper/2003.13951/) (2020)
- [How do neural networks see depth in single images?](https://mlsanity.com/paper/1905.07005/) (2019)
- [DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning](https://mlsanity.com/paper/2003.13446/) (2020)
- [Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark](https://mlsanity.com/paper/2108.03830/) (2021)
- [FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion](https://mlsanity.com/paper/2012.08270/) (2020)
- [Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction](https://mlsanity.com/paper/1903.07309/) (2019)
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://mlsanity.com/paper/2108.07628/) (2021)
- [Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation](https://mlsanity.com/paper/2010.01402/) (2020)
- [Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation](https://mlsanity.com/paper/2002.12114/) (2020)
- [Enhancing self-supervised monocular depth estimation with traditional visual odometry](https://mlsanity.com/paper/1908.03127/) (2019)

## Abstract (arXiv)

In recent years, self-supervised monocular depth estimation has drawn much attention since it frees of depth annotations and achieved remarkable results on standard benchmarks. However, most of existing methods only focus on either daytime or nighttime images, thus their performance degrades on the other domain because of the large domain shift between daytime and nighttime images. To address this problem, in this paper we propose a two-branch network named GlocalFuse-Depth for self-supervised depth estimation of all-day images. The daytime and nighttime image in input image pair are fed into the two branches: CNN branch and Transformer branch, respectively, where both fine-grained details and global dependency can be efficiently captured. Besides, a novel fusion module is proposed to fuse multi-dimensional features from the two branches. Extensive experiments demonstrate that GlocalFuse-Depth achieves state-of-the-art results for all-day images on the Oxford RobotCar dataset, which proves the superiority of our method.