paper-with-me

Papers

Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning Approach

2020-07-25 · Hemang Chawla, Matti Jukola, Terence Brouns, Elahe Arani, Bahram Zonooz

The ability to efficiently utilize crowdsourced visual data carries immense potential for the domains of large scale dynamic mapping and autonomous driving. However, state-of-the-art methods for crowdsourced 3D mapping assume prior knowledge of camera intrinsics. In this work, we propose a framework that estimates the 3D positions of semantically meaningful landmarks such as traffic signs without assuming known camera intrinsics, using only monocular color camera and GPS. We utilize multi-view geometry as well as deep learning based self-calibration, depth, and ego-motion estimation for traffic sign positioning, and show that combining their strengths is important for increasing the map coverage. To facilitate research on this task, we construct and make available a KITTI based 3D traffic sign ground truth positioning dataset. Using our proposed framework, we achieve an average single-journey relative and absolute positioning accuracy of 39cm and 1.26m respectively, on this dataset.

📄 PDF Abstract BibTeX arXiv:2007.12918

Code (1)

hemangchawla/3d-groundtruth-traffic-sign-positions 공식 구현

Tasks

Autonomous DrivingMotion EstimationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition

2018-11-03 · NeurIPS 2018 12 · Ricson Cheng, Ziyan Wang, Katerina Fragkiadaki

We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations…

3D ReconstructionObjectobject-detectionObject Detection+1

NeuTex: Neural Texture Mapping for Volumetric Neural Rendering

2021-03-01 · CVPR 2021 1 · Fanbo Xiang, Zexiang Xu, Miloš Hašan, Yannick Hold-Geoffroy 외

Recent work has demonstrated that volumetric scene representations combined with differentiable volume rendering can enable photo-realistic rendering for challenging scenes that mesh reconstruction fails on. However, the…

Neural Rendering

Towards Large-scale Building Attribute Mapping using Crowdsourced Images: Scene Text Recognition on Flickr and Problems to be Solved

2023-09-14 · Yao Sun, Anna Kruspe, Liqiu Meng, Yifan Tian 외

Crowdsourced platforms provide huge amounts of street-view images that contain valuable building information. This work addresses the challenges in applying Scene Text Recognition (STR) in crowdsourced street-view images…

AttributeScene Text RecognitionText Detection

End-to-End Generation of City-Scale Vectorized Maps by Crowdsourced Vehicles

2025-07-11 · Zebang Feng, Miao Fan, Bao Liu, Shengtong Xu 외 arxiv

High-precision vectorized maps are indispensable for autonomous driving, yet traditional LiDAR-based creation is costly and slow, while single-vehicle perception methods lack accuracy and robustness, particularly in adve…

Autonomous Driving

Weak Multi-View Supervision for Surface Mapping Estimation

2021-05-04 · Nishant Rai, Aidas Liaudanskas, Srinivas Rao, Rodrigo Ortiz Cayon 외

We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations. We learn the underlying surface geometry of common categories, such as human faces, cars, …

MULTI-VIEW LEARNING