Related papers: Slanted Stixels: A way to represent steep streets

Semantic segmentation is a powerful method to facilitate visual scene understanding. Each pixel is assigned a label according to a pre-defined list of object classes and semantic entities. This becomes very useful as a means to summarize…

Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In this paper, we explore how synthetic models alleviate the…

Convolutional neural networks have been widely applied to hyperspectral image classification. However, traditional convolutions can not effectively extract features for objects with irregular distributions. Recent methods attempt to address…

In the domain of 3D scene representation, 3D Gaussian Splatting (3DGS) has emerged as a pivotal technology. However, its application to large-scale, high-resolution scenes (exceeding 4k$\times$4k pixels) is hindered by the excessive…

With the rise of deep learning algorithms nowadays, scene image representation methods have achieved a significant performance boost in classification. However, the performance is still limited because the scene images are mostly complex…

Recently the dense Simultaneous Localization and Mapping (SLAM) based on neural implicit representation has shown impressive progress in hole filling and high-fidelity mapping. Nevertheless, existing methods either heavily rely on known…

Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the…

Generating scene graph to describe all the relations inside an image gains increasing interests these years. However, most of the previous methods use complicated structures with slow inference speed or rely on the external data, which…

Automatic building extraction from optical imagery remains a challenge due to, for example, the complexity of building shapes. Semantic segmentation is an efficient approach for this task. The latest development in deep convolutional neural…

Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or…

Achieving real-time and accuracy on embedded platforms has always been the pursuit of road segmentation methods. To this end, they have proposed many lightweight networks. However, they ignore the fact that roads are "stuff" (background or…

This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut's joint reasoning over scene semantics and geometry allows a robot to detect and…

Accurate surface geometry representation is crucial in 3D visual computing. Explicit representations, such as polygonal meshes, and implicit representations, like signed distance functions, each have distinct advantages, making efficient…

The widespread adoption of autonomous systems such as drones and assistant robots has created a need for real-time high-quality semantic scene segmentation. In this paper, we propose an efficient yet robust technique for on-the-fly dense…

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually computationally expensive, posing a challenge to the computing…

A skeleton representation of the human body has been proven to be effective for this task. The skeletons are presented in graphs form-like. However, the topology of a graph is not structured like Euclidean-based data. Therefore, a new set…

Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up approaches that try to group pixels into regions based on…

The sparse representation of signals defined on Euclidean domains has been successfully applied in signal processing. Bringing the power of sparse representations to non-regular domains is still a challenge, but promising approaches have…

While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual…

Geometry-aware modules are widely applied in recent deep learning architectures for scene representation and rendering. However, these modules require intrinsic camera information that might not be obtained accurately. In this paper, we…