paper-with-me

Papers

GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose

2018-03-06 · CVPR 2018 6 · Zhichao Yin, Jianping Shi

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and ego-motion estimation from videos. The three components are coupled by the nature of 3D scene geometry, jointly learned by our framework in an end-to-end manner. Specifically, geometric relationships are extracted over the predictions of individual modules and then combined as an image reconstruction loss, reasoning about static and dynamic scene parts separately. Furthermore, we propose an adaptive geometric consistency loss to increase robustness towards outliers and non-Lambertian regions, which resolves occlusions and texture ambiguities effectively. Experimentation on the KITTI driving dataset reveals that our scheme achieves state-of-the-art results in all of the three tasks, performing better than previously unsupervised methods and comparably with supervised ones.

📄 PDF Abstract BibTeX arXiv:1803.02276

Code (3)

yzcjtr/GeoNet 공식 구현 tf
raunaks13/GeoNet-PyTorch pytorch
yijie0710/GeoNet_pytorch pytorch

Tasks

Camera Pose EstimationImage ReconstructionMotion EstimationOptical Flow EstimationPose Estimation

Similar Papers 제목 키워드 기반

Unsupervised Learning of Dense Optical Flow, Depth and Egomotion from Sparse Event Data

2018-09-23 · Chengxi Ye, Anton Mitrokhin, Cornelia Fermüller, James A. Yorke 외

In this work we present a lightweight, unsupervised learning pipeline for \textit{dense} depth, optical flow and egomotion estimation from sparse event output of the Dynamic Vision Sensor (DVS). To tackle this low level …

DecoderGPUOptical Flow Estimation

Indoor GeoNet: Weakly Supervised Hybrid Learning for Depth and Pose Estimation

2018-11-19 · Amirreza Farnoosh, Sarah Ostadabbas

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspi…

Camera Pose EstimationPose Estimation

Dense Monocular Motion Segmentation Using Optical Flow and Pseudo Depth Map: A Zero-Shot Approach

2024-06-27 · Yuxiang Huang, Yuhao Chen, John Zelek

Motion segmentation from a single moving camera presents a significant challenge in the field of computer vision. This challenge is compounded by the unknown camera movements and the lack of depth information of the scen…

Depth EstimationMonocular Depth EstimationMotion SegmentationOptical Flow Estimation+1

Uncertainty-Driven Dense Two-View Structure from Motion

2023-02-01 · Weirong Chen, Suryansh Kumar, Fisher Yu

This work introduces an effective and practical solution to the dense two-view structure from motion (SfM) problem. One vital question addressed is how to mindfully use per-pixel optical flow correspondence between two f…

Depth EstimationOptical Flow EstimationPose EstimationVocal Bursts Valence Prediction

DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency

2018-09-05 · ECCV 2018 9 · Yuliang Zou, Zelun Luo, Jia-Bin Huang

We present an unsupervised learning framework for simultaneously training single-view depth prediction and optical flow estimation models using unlabeled video sequences. Existing unsupervised methods often exploit brigh…

Depth And Camera MotionDepth EstimationDepth PredictionOptical Flow Estimation