English
Related papers

Related papers: CIPHER: Culvert Inspection through Pairwise Frame …

200 papers

With the proliferation of small aerial vehicles, acquiring close up aerial imagery for high quality reconstruction of complex scenes is gaining importance. We present an adaptive view planning method to collect such images in an automated…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Cheng Peng , Volkan Isler

We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Zhaoxuan Zhang , Xiaoguang Han , Bo Dong , Tong Li , Baocai Yin , Xin Yang

Automatic reconstruction of 3D models from images using multi-view Structure-from-Motion methods has been one of the most fruitful outcomes of computer vision. These advances combined with the growing popularity of Micro Aerial Vehicles as…

Robotics · Computer Science 2016-11-15 Shreyansh Daftry , Christof Hoppe , Horst Bischof

Recent works have considered two qualitatively different approaches to overcome line-of-sight limitations of 3D sensors used for perception: cooperative perception and infrastructure-augmented perception. In this paper, motivated by…

Robotics · Computer Science 2024-06-28 Fawad Ahmad , Christina Suyong Shin , Weiwu Pang , Branden Leong , Pradipta Ghosh , Ramesh Govindan

Current approaches to 3D scene graph generation rely on dedicated depth sensors, such as LiDAR or RGB-D cameras, for metric 3D reconstruction. This limits deployment to specialized robotic platforms and excludes settings where only RGB…

Robotics · Computer Science 2026-05-19 Giorgia Modi , Davide Buoso , Giuseppe Averta , Daniele De Martini

Object tracking is a key challenge of computer vision with various applications that all require different architectures. Most tracking systems have limitations such as constraining all movement to a 2D plane and they often track only one…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Lars Bredereke , Yale Hartmann , Tanja Schultz

As a challenging vision-language (VL) task, Composed Image Retrieval (CIR) aims to retrieve target images using multimodal (image+text) queries. Although many existing CIR methods have attained promising performance, their reliance on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Haiwen Li , Delong Liu , Zhaohui Hou , Zhicheng Zhao , Fei Su

This paper presents an automated pipeline for processing multi-view satellite images to 3D digital surface models (DSM). The proposed pipeline performs automated geo-referencing and generates high-quality densely matched point clouds. In…

Computer Vision and Pattern Recognition · Computer Science 2019-10-08 Rongjun Qin

Creating a vision pipeline for different datasets to solve a computer vision task is a complex and time consuming process. Currently, these pipelines are developed with the help of domain experts. Moreover, there is no systematic structure…

Computer Vision and Pattern Recognition · Computer Science 2022-09-08 Aditya Kapoor , Nijil George , Vartika Sengar , Vighnesh Vatsal , Jayavardhana Gubbi

State-of-the-art techniques for monocular camera reconstruction predominantly rely on the Structure from Motion (SfM) pipeline. However, such methods often yield reconstruction outcomes that lack crucial scale information, and over time,…

Robotics · Computer Science 2023-10-10 Chunge Bai , Ruijie Fu , Xiang Gao

We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach. From an input monocular RGB video, the video frames are processed by a transformer network that fuses the observations into a volumetric feature grid…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Aljaž Božič , Pablo Palafox , Justus Thies , Angela Dai , Matthias Nießner

High-quality 4D reconstruction of human performance with complex interactions to various objects is essential in real-world scenarios, which enables numerous immersive VR/AR applications. However, recent advances still fail to provide…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 Zhuo Su , Lan Xu , Dawei Zhong , Zhong Li , Fan Deng , Shuxue Quan , Lu Fang

Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks…

The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Luoxi Zhang , Pragyan Shrestha , Yu Zhou , Chun Xie , Itaru Kitahara

We propose LiteReality, a novel pipeline that converts RGB-D scans of indoor environments into compact, realistic, and interactive 3D virtual replicas. LiteReality not only reconstructs scenes that visually resemble reality but also…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Zhening Huang , Xiaoyang Wu , Fangcheng Zhong , Hengshuang Zhao , Matthias Nießner , Joan Lasenby

This paper presents an innovative augmented reality pipeline tailored for museum environments, aimed at recognizing artworks and generating accurate 3D models from single images. By integrating two complementary pre-trained depth estimation…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Daniele Pannone , Alessia Castronovo , Maurizio Mancini , Gian Luca Foresti , Claudio Piciarelli , Rossana Gabrieli , Muhammad Yasir Bilal , Danilo Avola

Real-time, high-quality, 3D scanning of large-scale scenes is key to mixed reality and robotic applications. However, scalability brings challenges of drift in pose estimation, introducing significant errors in the accumulated model.…

Graphics · Computer Science 2017-02-09 Angela Dai , Matthias Nießner , Michael Zollhöfer , Shahram Izadi , Christian Theobalt

We present a fast and efficient volumetric capture and reconstruction system that processes either RGB-D or RGB-only input to generate 3D representations in the form of point clouds and Gaussian splats. For Gaussian splat reconstructions,…

Graphics · Computer Science 2025-12-19 Athanasios Charisoudis , Simone Croci , Lam Kit Yung , Pascal Frossard , Aljosa Smolic

Object detection applied to LiDAR point clouds is a relevant task in robotics, and particularly in autonomous driving. Single frame methods, predominant in the field, exploit information from individual sensor scans. Recent approaches…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Ernesto Lozano Calvo , Bernardo Taveira , Fredrik Kahl , Niklas Gustafsson , Jonathan Larsson , Adam Tonderski

A technique for the enhancement of point targets in clutter is described. The local 3-D spectrum at each pixel is estimated recursively. An optical flow-field for the textured background is then generated using the 3-D autocorrelation…

Computer Vision and Pattern Recognition · Computer Science 2015-08-25 Hugh L. Kennedy