Related papers: Enhancing Scene Coordinate Regression with Efficie…

SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mapping errors in…

Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…

Scene text recognition has received increased attention in the research community. Text in the wild often possesses irregular arrangements, typically including perspective text, curved text, oriented text. Most existing methods are hard to…

To enable autonomous robotic manipulation in unstructured environments, we present SegICP-DSR, a real- time, dense, semantic scene reconstruction and pose estimation algorithm that achieves mm-level pose accuracy and standard deviation (7.9…

While object detection methods traditionally make use of pixel-level masks or bounding boxes, alternative representations such as polygons or active contours have recently emerged. Among them, methods based on the regression of Fourier or…

Spatial-query-by-sketch is an intuitive tool to explore human spatial knowledge about geographic environments and to support communication with scene database queries. However, traditional sketch-based spatial search methods perform…

Video person re-identification attracts much attention in recent years. It aims to match image sequences of pedestrians from different camera views. Previous approaches usually improve this task from three aspects, including a) selecting…

Objective: Non-rigid image registration with high accuracy and efficiency is still a challenging task for medical image analysis. In this work, we present the spatially region-weighted correlation ratio (SRWCR) as a novel similarity measure…

LiDAR-based place recognition is an essential and challenging task both in loop closure detection and global relocalization. We propose Deep Scan Context (DSC), a general and discriminative global descriptor that captures the relationship…

We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches…

Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over-smoothed scene…

We introduce a high-fidelity neural implicit dense visual Simultaneous Localization and Mapping (SLAM) system, termed DF-SLAM. In our work, we employ dictionary factors for scene representation, encoding the geometry and appearance…

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…

We present a novel approach for super-resolution that utilizes implicit neural representation (INR) to effectively reconstruct and enhance low-resolution videos and images. By leveraging the capacity of neural networks to implicitly encode…

Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. The most recent deep learning based SISR methods focus…

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without…

Active camera relocalization (ACR) is a new problem in computer vision that significantly reduces the false alarm caused by image distortions due to camera pose misalignment in fine-grained change detection (FGCD). Despite the fruitful…

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which…

Compressed sensing (CS) is an innovative technique allowing to represent signals through a small number of their linear projections. In this paper we address the application of CS to the scenario of progressive acquisition of 2D visual…

Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of individual video frames, is an efficient…