paper-with-me

Papers

Stacked Homography Transformations for Multi-View Pedestrian Detection

2021-01-01 · ICCV 2021 10 · Liangchen Song, Jialian Wu, Ming Yang, Qian Zhang, Yuan Li, Junsong Yuan

Multi-view pedestrian detection aims to predict a bird's eye view (BEV) occupancy map from multiple camera views. This task is confronted with two challenges: how to establish the 3D correspondences from views to the BEV map and how to assemble occupancy information across views. In this paper, we propose a novel Stacked HOmography Transformations (SHOT) approach, which is motivated by approximating projections in 3D world coordinates via a stack of homographies. We first construct a stack of transformations for projecting views to the ground plane at different height levels. Then we design a soft selection module so that the network learns to predict the likelihood of the stack of transformations. Moreover, we provide an in-depth theoretical analysis on constructing SHOT and how well SHOT approximates projections in 3D world coordinates. SHOT is empirically verified to be capable of estimating accurate correspondences from individual views to the BEV map, leading to new state-of-the-art performance on standard evaluation benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Multiview DetectionPedestrian Detection

Similar Papers 제목 키워드 기반

Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention

2022-08-19 · Jinwoo Hwang, Philipp Benz, Tae-hoon Kim

Improving multi-view aggregation is integral for multi-view pedestrian detection, which aims to obtain a bird's-eye-view pedestrian occupancy map from images captured through a set of calibrated cameras. Inspired by the …

Multiview DetectionPedestrian Detection

HomE: Homography-Equivariant Video Representation Learning

2023-06-02 · Anirudh Sriram, Adrien Gaidon, Jiajun Wu, Juan Carlos Niebles 외

Recent advances in self-supervised representation learning have enabled more efficient and robust model performance without relying on extensive labeled data. However, most works are still focused on images, with few wor…

Action ClassificationAction RecognitionRepresentation LearningSelf-Supervised Learning

GridFace: Face Rectification via Learning Local Homography Transformations

2018-08-19 · ECCV 2018 9 · Erjin Zhou, Zhimin Cao, Jian Sun

In this paper, we propose a method, called GridFace, to reduce facial geometric variations and improve the recognition performance. Our method rectifies the face by local homography transformations, which are estimated b…

Face RecognitionImage Generation

Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations

2024-02-28 · Shen Cai, Zhanhao Wu, Lingxi Guo, Jiachun Wang 외

In this paper, we present two fast and interpretable decomposition methods for 2D homography, which are named Similarity-Kernel-Similarity (SKS) and Affine-Core-Affine (ACA) transformations respectively. Under the minima…

Computational Efficiency

HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps

2026-01-06 · Xuchang Zhong, Xu Cao, Jinke Feng, Hao Fang arxiv

Visual localization on standard-definition (SD) maps has emerged as a promising low-cost and scalable solution for autonomous driving. However, existing regression-based approaches often overlook inherent geometric prior…

Visual LocalizationAutonomous Driving