# A Deeper Insight into the UnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation

arXiv: https://arxiv.org/abs/1809.00969 · HTML: https://mlsanity.com/paper/1809.00969/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 11 of 11)

- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2110.08192/) (2021)
- [When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation](https://mlsanity.com/paper/2206.13850/) (2022)
- [GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Network](https://mlsanity.com/paper/2112.06782/) (2021)
- [Absolute distance prediction based on deep learning object detection and monocular depth estimation models](https://mlsanity.com/paper/2111.01715/) (2021)
- [Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus](https://mlsanity.com/paper/2409.12323/) (2024)
- [A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation](https://mlsanity.com/paper/2203.04812/) (2022)
- [Improving Depth Estimation using Location Information](https://mlsanity.com/paper/2112.13925/) (2021)
- [3D Object Aided Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.01768/) (2022)
- [DAPM: UAV Monocular Depth Estimation from Any Height, Pitch, Roll and FOV](https://mlsanity.com/paper/2607.21438/) (2026)

## Abstract (arXiv)

This paper presents an unsupervised deep learning framework called UnDEMoN for estimating dense depth map and 6-DoF camera pose information directly from monocular images. The proposed network is trained using unlabeled monocular stereo image pairs and is shown to provide superior performance in depth and ego-motion estimation compared to the existing state-of-the-art. These improvements are achieved by introducing a new objective function that aims to minimize spatial as well as temporal reconstruction losses simultaneously. These losses are defined using bi-linear sampling kernel and penalized using the Charbonnier penalty function. The objective function, thus created, provides robustness to image gradient noises thereby improving the overall estimation accuracy without resorting to any coarse to fine strategies which are currently prevalent in the literature. Another novelty lies in the fact that we combine a disparity-based depth estimation network with a pose estimation network to obtain absolute scale-aware 6 DOF Camera pose and superior depth map. The effectiveness of the proposed approach is demonstrated through performance comparison with the existing supervised and unsupervised methods on the KITTI driving dataset.