English
Related papers

Related papers: CAPE: Camera View Position Embedding for Multi-Vie…

200 papers

We hypothesize that an agent that can look around in static scenes can learn rich visual representations applicable to 3D object tracking in complex dynamic scenes. We are motivated in this pursuit by the fact that the physical world itself…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Adam W. Harley , Shrinidhi K. Lakshmikanth , Paul Schydlo , Katerina Fragkiadaki

Visual localization, i.e., determining the position and orientation of a vehicle with respect to a map, is a key problem in autonomous driving. We present a multicamera visual inertial localization algorithm for large scale environments. To…

Robotics · Computer Science 2019-05-16 Marcel Geppert , Peidong Liu , Zhaopeng Cui , Marc Pollefeys , Torsten Sattler

3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Chenshu Hou , Liang Peng , Xiaopei Wu , Xiaofei He , Wenxiao Wang

We describe MPSE: a Multi-Perspective Simultaneous Embedding method for visualizing high-dimensional data, based on multiple pairwise distances between the data points. Specifically, MPSE computes positions for the points in 3D and provides…

Data Structures and Algorithms · Computer Science 2020-08-07 Md Iqbal Hossain , Vahan Huroyan , Stephen Kobourov , Raymundo Navarrete

Relative position embedding has become a standard mechanism for encoding positional information in Transformers. However, existing formulations are typically limited to a fixed geometric space, namely 1D sequences or regular 2D/3D grids,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Yichen Xie , Depu Meng , Chensheng Peng , Yihan Hu , Quentin Herau , Masayoshi Tomizuka , Wei Zhan

Current Transformer-based methods for small object detection continue emerging, yet they have still exhibited significant shortcomings. This paper introduces HeatMap Position Embedding (HMPE), a novel Transformer Optimization technique that…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 YangChen Zeng

In this paper, we propose a method for initial camera pose estimation from just a single image which is robust to viewing conditions and does not require a detailed model of the scene. This method meets the growing need of easy deployment…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Matthieu Zins , Gilles Simon , Marie-Odile Berger

Environmental perception with the multi-modal fusion of radar and camera is crucial in autonomous driving to increase accuracy, completeness, and robustness. This paper focuses on utilizing millimeter-wave (MMW) radar and camera sensor…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Taohua Zhou , Yining Shi , Junjie Chen , Kun Jiang , Mengmeng Yang , Diange Yang

In embodied intelligence systems, a key component is 3D perception algorithm, which enables agents to understand their surrounding environments. Previous algorithms primarily rely on point cloud, which, despite offering precise geometric…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Xuewu Lin , Tianwei Lin , Lichao Huang , Hongyu Xie , Zhizhong Su

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Kejie Li , Daniel DeTone , Steven Chen , Minh Vo , Ian Reid , Hamid Rezatofighi , Chris Sweeney , Julian Straub , Richard Newcombe

Camera-based 3D object detection and tracking are central to autonomous driving, yet precise 3D object localization remains fundamentally constrained by depth ambiguity when no expensive, depth-rich online LiDAR is available at inference.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Markus Käppeler , Özgün Çiçek , Yakov Miron , Abhinav Valada

Traditional 2D pose estimation models are limited by their category-specific design, making them suitable only for predefined object categories. This restriction becomes particularly challenging when dealing with novel objects due to the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Or Hirschorn , Shai Avidan

This study introduces a novel approach to online embedding of multi-scale CLIP (Contrastive Language-Image Pre-Training) features into 3D maps. By harnessing CLIP, this methodology surpasses the constraints of conventional…

Robotics · Computer Science 2024-03-28 Shun Taguchi , Hideki Deguchi

Simultaneous perception of 2D objects in perspective view and 3D objects in Bird's Eye View (BEV) is challenging for multi-camera autonomous driving. Existing two-stage pipelines use 2D results only as a one-time cue for 3D detection. We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yingqi Tang , Zhaotie Meng , Erkang Cheng , Haibin Ling

6D object pose estimation problem has been extensively studied in the field of Computer Vision and Robotics. It has wide range of applications such as robot manipulation, augmented reality, and 3D scene understanding. With the advent of…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Negar Nejatishahidin , Pooya Fayyazsanavi

We present an approach for aggregating a sparse set of views of an object in order to compute a semi-implicit 3D representation in the form of a volumetric feature grid. Key to our approach is an object-centric canonical 3D coordinate…

Computer Vision and Pattern Recognition · Computer Science 2020-07-22 Shubham Tulsiani , Or Litany , Charles R. Qi , He Wang , Leonidas J. Guibas

3D mapping in dynamic environments poses a challenge for modern researchers in robotics and autonomous transportation. There are no universal representations for dynamic 3D scenes that incorporate multimodal data such as images, point…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Dmitry Yudin

Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Zhihong Wei

Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people. However, cameras generally capture human poses in 2D as images and videos, which can have significant appearance variations across…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Ting Liu , Jennifer J. Sun , Long Zhao , Jiaping Zhao , Liangzhe Yuan , Yuxiao Wang , Liang-Chieh Chen , Florian Schroff , Hartwig Adam

Accurate localization on autonomous driving cars is essential for autonomy and driving safety, especially for complex urban streets and search-and-rescue subterranean environments where high-accurate GPS is not available. However current…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Peng Yin , Lingyun Xu , Ziyue Feng , Anton Egorov , Bing Li