paper-with-me

Papers

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency

2021-02-04 · Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we highlight the fundamental difference between inverse and forward projection while modeling the individual motion of each rigid object, and propose a geometrically correct projection pipeline using a neural forward projection module. Second, we design a unified instance-aware photometric and geometric consistency loss that holistically imposes self-supervisory signals for every background and object region. Lastly, we introduce a general-purpose auto-annotation scheme using any off-the-shelf instance segmentation and optical flow models to produce video instance segmentation maps that will be utilized as input to our training pipeline. These proposed elements are validated in a detailed ablation study. Through extensive experiments conducted on the KITTI and Cityscapes dataset, our framework is shown to outperform the state-of-the-art depth and motion estimation methods. Our code, dataset, and models are available at https://github.com/SeokjuLee/Insta-DM .

📄 PDF Abstract BibTeX arXiv:2102.02629

Code (1)

SeokjuLee/Insta-DM 공식 구현 pytorch

Tasks

Instance SegmentationMonocular Depth EstimationMotion EstimationOptical Flow EstimationSemantic SegmentationUnsupervised Monocular Depth EstimationVideo Instance Segmentation

Similar Papers 제목 키워드 기반

Instance-aware multi-object self-supervision for monocular depth prediction

2022-03-02 · Houssem Boulahbal, Adrian Voicila, Andrew Comport

This paper proposes a self-supervised monocular image-to-depth prediction framework that is trained with an end-to-end photometric loss that handles not only 6-DOF camera motion but also 6-DOF moving object instances. Se…

Depth EstimationDepth PredictionObjectPose Estimation+1

MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors

2024-06-01 · Qingming Liu, YuAn Liu, Jiepeng Wang, Xianqiang Lyv 외

In this paper, we propose MoDGS, a new pipeline to render novel views of dy namic scenes from a casually captured monocular video. Previous monocular dynamic NeRF or Gaussian Splatting methods strongly rely on the rapid …

Depth EstimationNeRF

Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling

2024-08-14 · Ruofeng Wei, Bin Li, Kai Chen, Yiyao Ma 외

Scale-aware monocular depth estimation poses a significant challenge in computer-aided endoscopic navigation. However, existing depth estimation methods that do not consider the geometric priors struggle to learn the abs…

Depth EstimationMonocular Depth Estimation

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

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