paper-with-me

홈 › Papers

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

2022-06-08 · Kieran Saunders, George Vogiatzis, Luis J. Manso

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.

📄 PDF Abstract BibTeX arXiv:2206.03799

Code (1)

kieran514/dyna-dm 공식 구현 pytorch

Tasks

Autonomous DrivingDepth EstimationGPUMonocular Depth EstimationUnsupervised Monocular Depth Estimation

Similar Papers 제목 키워드 기반

AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving

2025-07-16 · Jiawei Xu, Kai Deng, Zexin Fan, Shenlong Wang 외 arxiv

Modeling and rendering dynamic urban driving scenes is crucial for self-driving simulation. Current high-quality methods typically rely on costly manual object tracklet annotations, while self-supervised approaches fail …

Autonomous Driving

DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting

2025-11-10 · Chenpeng Su, Wenhua Wu, Chensheng Peng, Tianchen Deng 외 arxiv

Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on costly human annotations and lack scalabilit…

Autonomous Driving

Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth

2022-03-29 · Ziyue Feng, Liang Yang, Longlong Jing, HaiYan Wang 외

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by…

Depth EstimationDepth PredictionDisentanglementMonocular Depth Estimation+4

Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes

2023-12-23 · Kaichen Zhou, Jia-Wang Bian, Jian-Qing Zheng, JiaXing Zhong 외

Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper, we present Manydepth2, to achieve prec…

Camera Pose EstimationComputational EfficiencyDepth EstimationMonocular Depth Estimation+1

DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos

2024-03-09 · Xiuzhe Wu, Xiaoyang Lyu, Qihao Huang, Yong liu 외

Although considerable advancements have been attained in self-supervised depth estimation from monocular videos, most existing methods often treat all objects in a video as static entities, which however violates the dyn…

Depth EstimationDisentanglementMotion DisentanglementMotion Estimation+3