相关论文: CM-EVS: Sparse Panoramic RGB-D-Pose Data for Compl…

High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their generation typically relies on robust ground filtering (GF) to separate point clouds across…

Estimating a dense and accurate depth map is the key requirement for autonomous driving and robotics. Recent advances in deep learning have allowed depth estimation in full resolution from a single image. Despite this impressive result,…

3D pose estimation from sparse multi-views is a critical task for numerous applications, including action recognition, sports analysis, and human-robot interaction. Optimization-based methods typically follow a two-stage pipeline, first…

The well-established modular autonomous driving system is decoupled into different standalone tasks, e.g. perception, prediction and planning, suffering from information loss and error accumulation across modules. In contrast, end-to-end…

We present a novel approach that converts partial and noisy RGB-D scans into high-quality 3D scene reconstructions by inferring unobserved scene geometry. Our approach is fully self-supervised and can hence be trained solely on real-world,…

Multi-view visual reasoning is essential for intelligent systems that must understand complex environments from sparse and discrete viewpoints, yet existing research has largely focused on single-image or temporally dense video settings. In…

While a great variety of 3D cameras have been introduced in recent years, most publicly available datasets for object recognition and pose estimation focus on one single camera. In this work, we present a dataset of 32 scenes that have been…

With the increasing reliance of self-driving and similar robotic systems on robust 3D vision, the processing of LiDAR scans with deep convolutional neural networks has become a trend in academia and industry alike. Prior attempts on the…

The broad scope of obstacle avoidance has led to many kinds of computer vision-based approaches. Despite its popularity, it is not a solved problem. Traditional computer vision techniques using cameras and depth sensors often focus on…

Depth completion from sparse LiDAR measurements and corresponding RGB images is a prerequisite for accurate 3D perception in robotic systems. Existing methods achieve high accuracy on standard benchmarks but rely on heavy backbone…

We consider the problem of 3D object pose estimation. While much recent work has focused on the RGB domain, the reliance on accurately annotated images limits their generalizability and scalability. On the other hand, the easily available…

Replicating a user's pose from only wearable sensors is important for many AR/VR applications. Most existing methods for motion tracking avoid environment interaction apart from foot-floor contact due to their complex dynamics and hard…

360{\deg} images are widely available over the last few years. This paper proposes a new technique for single 360{\deg} image depth prediction under open environments. Depth prediction from a 360{\deg} single image is not easy for two…

The advancement of RS technology has enabled high-resolution Earth observation; however, interpreting these images using modern VFMs remains a significant challenge. Unlike object-centric natural images, RS imagery is fundamentally…

Event cameras are bio-inspired sensors that respond to per-pixel brightness changes in the form of asynchronous and sparse "events". Recently, pattern recognition algorithms, such as learning-based methods, have made significant progress…

Estimating 6D poses of objects is an essential computer vision task. However, most conventional approaches rely on camera data from a single perspective and therefore suffer from occlusions. We overcome this issue with our novel multi-view…

Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough images to work with,…

Accurate depth estimation plays a critical role in the navigation of endoscopic surgical robots, forming the foundation for 3D reconstruction and safe instrument guidance. Fine-tuning pretrained models heavily relies on endoscopic surgical…

When exploring new areas, robotic systems generally exclusively plan and execute controls over geometry that has been directly measured. When entering space that was previously obstructed from view such as turning corners in hallways or…

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…