Related papers: D2S: Representing sparse descriptors and 3D coordi…

In recent years, coordinate-based neural implicit representations have shown promising results for the task of Simultaneous Localization and Mapping (SLAM). While achieving impressive performance on small synthetic scenes, these methods…

Accurate and robust visual localization under a wide range of viewing condition variations including season and illumination changes, as well as weather and day-night variations, is the key component for many computer vision and robotics…

Objective: The computation of anatomical information and laparoscope position is a fundamental block of surgical navigation in Minimally Invasive Surgery (MIS). Recovering a dense 3D structure of surgical scene using visual cues remains a…

The ultimate aim of image restoration like denoising is to find an exact correlation between the noisy and clear image domains. But the optimization of end-to-end denoising learning like pixel-wise losses is performed in a sample-to-sample…

This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small…

For relocalization in large-scale point clouds, we propose the first approach that unifies global place recognition and local 6DoF pose refinement. To this end, we design a Siamese network that jointly learns 3D local feature detection and…

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tasks such as semantic…

Although various visual localization approaches exist, such as scene coordinate regression and camera pose regression, these methods often struggle with optimization complexity or limited accuracy. To address these challenges, we explore…

Visual relocalization, which estimates the 6-degree-of-freedom (6-DoF) camera pose from query images, is fundamental to remote sensing and UAV applications. Existing methods face inherent trade-offs: image-based retrieval and pose…

We propose a novel concept to directly match feature descriptors extracted from RGB images, with feature descriptors extracted from 3D point clouds. We use this concept to localize the position and orientation (pose) of the camera of a…

LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Yet, small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a new framework to…

Distribution-to-distribution (D2D) point cloud registration techniques such as the Normal Distributions Transform (NDT) can align point clouds sampled from unstructured scenes and provide accurate bounds of their own solution error…

Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their localization…

We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images to an embedding space, we establish a common low-level…

This paper presents a novel camera relocalization method, STDLoc, which leverages Feature Gaussian as scene representation. STDLoc is a full relocalization pipeline that can achieve accurate relocalization without relying on any pose prior.…

Place recognition is a core component of Simultaneous Localization and Mapping (SLAM) algorithms. Particularly in visual SLAM systems, previously-visited places are recognized by measuring the appearance similarity between images…

Current global re-localization algorithms are built on top of localization and mapping methods andheavily rely on scan matching and direct point cloud feature extraction and therefore are vulnerable infeatureless demanding environments like…

We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images and 3D LiDAR point clouds. We present a novel method,…

In this paper, we propose an easily trained yet powerful representation learning approach with performance highly competitive to deep neural networks in a digital pathology image segmentation task. The method, called sparse coding driven…

In this work, we present a novel method to learn a local cross-domain descriptor for 2D image and 3D point cloud matching. Our proposed method is a dual auto-encoder neural network that maps 2D and 3D input into a shared latent space…