English
Related papers

Related papers: LocoNeRF: A NeRF-based Approach for Local Structur…

200 papers

Non-Rigid Structure-from-Motion (NRSfM) is a classic 3D vision problem, where a 2D sequence is taken as input to estimate the corresponding 3D sequence. Recently, the deep neural networks have greatly advanced the task of NRSfM. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Hui Deng , Jiawei Shi , Zhen Qin , Yiran Zhong , Yuchao Dai

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on accurate camera pose priors. Existing approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Qingsong Yan , Qiang Wang , Kaiyong Zhao , Jie Chen , Bo Li , Xiaowen Chu , Fei Deng

This paper addresses the problem of Structure from Motion (SfM) for indoor panoramic image streams, extremely challenging even for the state-of-the-art due to the lack of textures and minimal parallax. The key idea is the fusion of…

Computer Vision and Pattern Recognition · Computer Science 2016-12-06 Satoshi Ikehata , Ivaylo Boyadzhiev , Qi Shan , Yasutaka Furukawa

Can we localize a robot on a map only using monocular vision? This study presents NuRF, an adaptive and nudged particle filter framework in radiance fields for 6-DoF robot visual localization. NuRF leverages recent advancements in radiance…

Robotics · Computer Science 2025-03-27 Wugang Meng , Tianfu Wu , Huan Yin , Fumin Zhang

We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic…

Computer Vision and Pattern Recognition · Computer Science 2023-07-17 Tang Tao , Longfei Gao , Guangrun Wang , Yixing Lao , Peng Chen , Hengshuang Zhao , Dayang Hao , Xiaodan Liang , Mathieu Salzmann , Kaicheng Yu

Robust visual localization for urban vehicles remains challenging and unsolved. The limitation of computation efficiency and memory size has made it harder for large-scale applications. Since semantic information serves as a stable and…

Robotics · Computer Science 2020-10-14 Ziwei Liao , Jieqi Shi , Xianyu Qi , Xiaoyu Zhang , Wei Wang , Yijia He , Ran Wei , Xiao Liu

Novel view synthesis (NVS) approaches such as NeRFs or 3DGS can produce photo-realistic 3D scene representation from a set of images with known extrinsic and intrinsic parameters. The necessary camera poses and calibrations are typically…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Jhacson Meza , Martin R. Oswald , Torsten Sattler

We revisit scene-level 3D object detection as the output of an object-centric framework capable of both localization and mapping using 3D oriented boxes as the underlying geometric primitive. While existing 3D object detection approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Justin Lazarow , Kai Kang , Afshin Dehghan

A critical obstacle preventing NeRF models from being deployed broadly in the wild is their reliance on accurate camera poses. Consequently, there is growing interest in extending NeRF models to jointly optimize camera poses and scene…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Zezhou Cheng , Carlos Esteves , Varun Jampani , Abhishek Kar , Subhransu Maji , Ameesh Makadia

Neural implicit representations such as NeRF have revolutionized 3D scene representation with photo-realistic quality. However, existing methods for visual localization within NeRF representations suffer from inefficiency and scalability…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Huaiji Zhou , Bing Wang , Changhao Chen

The images and sounds that we perceive undergo subtle but geometrically consistent changes as we rotate our heads. In this paper, we use these cues to solve a problem we call Sound Localization from Motion (SLfM): jointly estimating camera…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Ziyang Chen , Shengyi Qian , Andrew Owens

We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Jianlin Liu , Qiang Nie , Yong Liu , Chengjie Wang

The Structure from Motion (SfM) challenge in computer vision is the process of recovering the 3D structure of a scene from a series of projective measurements that are calculated from a collection of 2D images, taken from different…

Computer Vision and Pattern Recognition · Computer Science 2023-04-06 Joseph Rowell

Online reconstructing and rendering of large-scale indoor scenes is a long-standing challenge. SLAM-based methods can reconstruct 3D scene geometry progressively in real time but can not render photorealistic results. While NeRF-based…

Computer Vision and Pattern Recognition · Computer Science 2023-04-19 Yiming Gao , Yan-Pei Cao , Ying Shan

Reconstructing from multi-view images is a longstanding problem in 3D vision, where neural radiance fields (NeRFs) have shown great potential and get realistic rendered images of novel views. Currently, most NeRF methods either require…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Xin Wen , Xuening Zhu , Renjiao Yi , Zhifeng Wang , Chenyang Zhu , Kai Xu

This paper proposes a new method for Non-Rigid Structure-from-Motion (NRSfM) from a long monocular video sequence observing a non-rigid object performing recurrent and possibly repetitive dynamic action. Departing from the traditional idea…

Computer Vision and Pattern Recognition · Computer Science 2018-04-19 Xiu Li , Hongdong Li , Hanbyul Joo , Yebin Liu , Yaser Sheikh

Neural Radiance Fields (NeRFs) are trained to minimize the rendering loss of predicted viewpoints. However, the photometric loss often does not provide enough information to disambiguate between different possible geometries yielding the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-06 Anita Rau , Josiah Aklilu , F. Christopher Holsinger , Serena Yeung-Levy

This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Yuxi Xiao , Nan Xue , Tianfu Wu , Gui-Song Xia

Neural Radiance Field (NeRF) has widely received attention in Sparse-View Computed Tomography (SVCT) reconstruction tasks as a self-supervised deep learning framework. NeRF-based SVCT methods represent the desired CT image as a continuous…

Image and Video Processing · Electrical Eng. & Systems 2022-11-08 Qing Wu , Xin Li , Hongjiang Wei , Jingyi Yu , Yuyao Zhang

Efficient and accurate camera pose estimation forms the foundational requirement for dense reconstruction in autonomous navigation, robotic perception, and virtual simulation systems. This paper addresses the challenge via cuSfM, a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Jingrui Yu , Jun Liu , Kefei Ren , Joydeep Biswas , Rurui Ye , Keqiang Wu , Chirag Majithia , Di Zeng