# Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps

arXiv: https://arxiv.org/abs/2206.03799 · HTML: https://mlsanity.com/paper/2206.03799/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 8 Jun 2022.

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

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)
- [Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos](https://mlsanity.com/paper/1811.06152/) (2018)
- [Feature-metric Loss for Self-supervised Learning of Depth and Egomotion](https://mlsanity.com/paper/2007.10603/) (2020)
- [Occlusion Aware Unsupervised Learning of Optical Flow](https://mlsanity.com/paper/1711.05890/) (2017)
- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [Learning to Segment Rigid Motions from Two Frames](https://mlsanity.com/paper/2101.03694/) (2021)
- [Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation](https://mlsanity.com/paper/1804.04259/) (2018)
- [A Study of the Generalizability of Self-Supervised Representations](https://mlsanity.com/paper/2109.09150/) (2021)
- [Enhancing self-supervised monocular depth estimation with traditional visual odometry](https://mlsanity.com/paper/1908.03127/) (2019)
- [Self-Supervised Monocular Scene Decomposition and Depth Estimation](https://mlsanity.com/paper/2110.11275/) (2021)
- [Instance-aware multi-object self-supervision for monocular depth prediction](https://mlsanity.com/paper/2203.00809/) (2022)

## Built on by (most cited first, 3 of 3)

- [Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes](https://mlsanity.com/paper/2310.18887/) (2023)
- [RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes](https://mlsanity.com/paper/2403.09419/) (2024)
- [BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2407.20437/) (2024)

## Abstract (arXiv)

Self-supervised monocular depth estimation has been a subject of intense study in recent years, because of its applications in robotics and autonomous driving. Much of the recent work focuses on improving depth estimation by increasing architecture complexity. This paper shows that state-of-the-art performance can also be achieved by improving the learning process rather than increasing model complexity. More specifically, we propose (i) disregarding small potentially dynamic objects when training, and (ii) employing an appearance-based approach to separately estimate object pose for truly dynamic objects. We demonstrate that these simplifications reduce GPU memory usage by 29% and result in qualitatively and quantitatively improved depth maps. The code is available at https://github.com/kieran514/Dyna-DM.