Image to Point Cloud Registration

9 papers with code • 1 benchmarks • 2 datasets

Given a query image and a scene of point cloud, get the camera pose according to them.


Most implemented papers

3D Path Planning from a Single 2D Fluoroscopic Image for Robot Assisted Fenestrated Endovascular Aortic Repair

jianqingzheng/path_planning_for_FEVAR 16 Sep 2018

The current standard of intra-operative navigation during Fenestrated Endovascular Aortic Repair (FEVAR) calls for need of 3D alignments between inserted devices and aortic branches.

DeepI2P: Image-to-Point Cloud Registration via Deep Classification

lijx10/DeepI2P CVPR 2021

This paper presents DeepI2P: a novel approach for cross-modality registration between an image and a point cloud.

Learning general and distinctive 3D local deep descriptors for point cloud registration

fabiopoiesi/gedi 21 May 2021

An effective 3D descriptor should be invariant to different geometric transformations, such as scale and rotation, robust to occlusions and clutter, and capable of generalising to different application domains.

CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence

rsy6318/CorrI2P 12 Jul 2022

Motivated by the intuition that the critical step of localizing a 2D image in the corresponding 3D point cloud is establishing 2D-3D correspondence between them, we propose the first feature-based dense correspondence framework for addressing the image-to-point cloud registration problem, dubbed CorrI2P, which consists of three modules, i. e., feature embedding, symmetric overlapping region detection, and pose estimation through the established correspondence.

GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer

qinzheng93/geotransformer 25 Jul 2023

They seek correspondences over downsampled superpoints, which are then propagated to dense points.

EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization

minnjung/ep2p-loc ICCV 2023

Visual localization is the task of estimating a 6-DoF camera pose of a query image within a provided 3D reference map.

FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators

WHU-USI3DV/FreeReg 5 Oct 2023

Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration.

Colmap-PCD: An Open-source Tool for Fine Image-to-point cloud Registration

xiaobaiiiiii/colmap-pcd 9 Oct 2023

In contrast, mapping methods based on LiDAR scans are popular in large-scale urban scene reconstruction due to their precise distance measurements, a capability fundamentally absent in visual-based approaches.

Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark

DavidBoja/exhaustive-grid-search Machine Vision and Applications 2024

The FP benchmark addresses the limitations of the current benchmarks: lack of data and parameter range variability, and allows to evaluate the strengths and weaknesses of a 3D registration method w. r. t.