mlsanityData to 14 Oct 2026

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

arXiv 2206.03799 ↗First posted 8 Jun 2022cs.CVcited by 3

Not on the map. Why?

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.

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

25 of 31 references.

References · 25

  1. 2017Mask R-CNNcited by 7,277
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  4. 2021Vision Transformers for Dense Predictioncited by 1,803
  5. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  6. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  7. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  8. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  9. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  10. 2018Pyramid Stereo Matching Networkcited by 489
  11. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  12. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
13 more
  1. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  2. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  3. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  4. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  5. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  6. 2017Occlusion Aware Unsupervised Learning of Optical Flowcited by 101
  7. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  8. 2021Learning to Segment Rigid Motions from Two Framescited by 46
  9. 2018Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimationcited by 38
  10. 2021A Study of the Generalizability of Self-Supervised Representationscited by 18
  11. 2019Enhancing self-supervised monocular depth estimation with traditional visual odometrycited by 9
  12. 2021Self-Supervised Monocular Scene Decomposition and Depth Estimationcited by 8
  13. 2022Instance-aware multi-object self-supervision for monocular depth predictioncited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2023Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenescited by 20
  2. 2024RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenescited by 14
  3. 2024BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimationcited by 2