Related papers: HyperDet3D: Learning a Scene-conditioned 3D Object…

3D semantic occupancy prediction aims to reconstruct the 3D geometry and semantics of the surrounding environment. With dense voxel labels, prior works typically formulate it as a dense segmentation task, independently classifying each…

We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D…

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

As a fundamental task for indoor scene understanding, 3D object detection has been extensively studied, and the accuracy on indoor point cloud data has been substantially improved. However, existing researches have been conducted on limited…

Deep learning has shown state-of-art classification performance on datasets such as ImageNet, which contain a single object in each image. However, multi-object classification is far more challenging. We present a unified framework which…

3D instance segmentation is fundamental to geometric understanding of the world around us. Existing methods for instance segmentation of 3D scenes rely on supervision from expensive, manual 3D annotations. We propose UnScene3D, the first…

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…

3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to…

Semantic 3D scene understanding is a problem of critical importance in robotics. While significant advances have been made in simultaneous localization and mapping algorithms, robots are still far from having the common sense knowledge…

Robots cannot yet match humans' ability to rapidly learn the shapes of novel 3D objects and recognize them robustly despite clutter and occlusion. We present Bayes3D, an uncertainty-aware perception system for structured 3D scenes, that…

The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature…

We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation…

Unsupervised learning for geometric perception (depth, optical flow, etc.) is of great interest to autonomous systems. Recent works on unsupervised learning have made considerable progress on perceiving geometry; however, they usually…

Transformer-based methods have demonstrated superior performance for monocular 3D object detection recently, which aims at predicting 3D attributes from a single 2D image. Most existing transformer-based methods leverage both visual and…

Vision-based 3D Semantic Scene Completion (SSC) has received growing attention due to its potential in autonomous driving. While most existing approaches follow an ego-centric paradigm by aggregating and diffusing features over the entire…

The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of…

In this paper, we propose a self-supervised learningmethod for multi-object pose estimation. 3D object under-standing from 2D image is a challenging task that infers ad-ditional dimension from reduced-dimensional information.In particular,…

The quality of life of many people could be improved by autonomous humanoid robots in the home. To function in the human world, a humanoid household robot must be able to locate itself and perceive the environment like a human; scene…

Current methods aggregate multi-level features or introduce edge and skeleton to get more refined saliency maps. However, little attention is paid to how to obtain the complete salient object in cluttered background, where the targets are…

3D scene understanding plays a vital role in vision-based autonomous driving. While most existing methods focus on 3D object detection, they have difficulty describing real-world objects of arbitrary shapes and infinite classes. Towards a…