paper-with-me

홈 › Papers

GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency

2018-11-17 · Yunze Man, Xinshuo Weng, Xi Li, Kris Kitani

We focus on estimating the 3D orientation of the ground plane from a single image. We formulate the problem as an inter-mingled multi-task prediction problem by jointly optimizing for pixel-wise surface normal direction, ground plane segmentation, and depth estimates. Specifically, our proposed model, GroundNet, first estimates the depth and surface normal in two separate streams, from which two ground plane normals are then computed deterministically. To leverage the geometric correlation between depth and normal, we propose to add a consistency loss on top of the computed ground plane normals. In addition, a ground segmentation stream is used to isolate the ground regions so that we can selectively back-propagate parameter updates through only the ground regions in the image. Our method achieves the top-ranked performance on ground plane normal estimation and horizon line detection on the real-world outdoor datasets of ApolloScape and KITTI, improving the performance of previous art by up to 17.7% relatively.

📄 PDF Abstract BibTeX arXiv:1811.07222

Code (0)

등록된 구현이 없습니다.

Tasks

Line DetectionSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

MonoGround: Detecting Monocular 3D Objects from the Ground

2022-06-15 · CVPR 2022 1 · Zequn Qin, Xi Li

Monocular 3D object detection has attracted great attention for its advantages in simplicity and cost. Due to the ill-posed 2D to 3D mapping essence from the monocular imaging process, monocular 3D object detection suffe…

3D Object DetectionDepth EstimationMonocular 3D Object DetectionObject+2

Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving

2014-06-01 · CVPR 2014 6 · Shiyu Song, Manmohan Chandraker

Scale drift is a crucial challenge for monocular autonomous driving to emulate the performance of stereo. This paper presents a real-time monocular SFM system that corrects for scale drift using a novel cue combination f…

Autonomous DrivingObjectobject-detectionObject Detection+1

NDDepth: Normal-Distance Assisted Monocular Depth Estimation

2023-09-19 · ICCV 2023 1 · Shuwei Shao, Zhongcai Pei, Weihai Chen, Xingming Wu 외

Monocular depth estimation has drawn widespread attention from the vision community due to its broad applications. In this paper, we propose a novel physics (geometry)-driven deep learning framework for monocular depth e…

Depth EstimationDepth PredictionMonocular Depth Estimation

Ground Plane Estimation using a Hidden Markov Model

2014-06-01 · CVPR 2014 6 · Ralf Dragon, Luc van Gool

We focus on the problem of estimating the ground plane orientation and location in monocular video sequences from a moving observer. Our only assumptions are that the 3D ego motion t and the ground plane normal n are ort…

NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion

2023-11-13 · Shuwei Shao, Zhongcai Pei, Weihai Chen, Peter C. Y. Chen 외

Over the past few years, monocular depth estimation and completion have been paid more and more attention from the computer vision community because of their widespread applications. In this paper, we introduce novel phy…

Depth EstimationMonocular Depth Estimation