Related papers: GroundNet: Monocular Ground Plane Normal Estimatio…

The precise point cloud ground segmentation is a crucial prerequisite of virtually all perception tasks for LiDAR sensors in autonomous vehicles. Especially the clustering and extraction of objects from a point cloud usually relies on an…

This paper introduces an approach to produce accurate 3D detection boxes for objects on the ground using single monocular images. We do so by merging 2D visual cues, 3D object dimensions, and ground plane constraints to produce boxes that…

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a monocular image due to the geometric information loss during imagery projection. We propose…

We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric context in existing methods impedes their ability to…

Unsupervised learning of depth from indoor monocular videos is challenging as the artificial environment contains many textureless regions. Fortunately, the indoor scenes are full of specific structures, such as planes and lines, which…

Structure from motion (SFM) and ground plane homography estimation are critical to autonomous driving and other robotics applications. Recently, much progress has been made in using deep neural networks for SFM and homography estimation…

We introduce Sky2Ground, a three-view dataset designed for varying altitude camera localization, correspondence learning, and reconstruction. The dataset combines structured synthetic imagery with real, in-the-wild images, providing both…

In this paper, we introduce a novel approach for ground plane normal estimation of wheeled vehicles. In practice, the ground plane is dynamically changed due to braking and unstable road surface. As a result, the vehicle pose, especially…

Unifying the correlative single-view satellite image building extraction and height estimation tasks indicates a promising way to share representations and acquire generalist model for large-scale urban 3D reconstruction. However, the…

Geometry plays a significant role in monocular 3D object detection. It can be used to estimate object depth by using the perspective projection between object's physical size and 2D projection in the image plane, which can introduce…

Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which…

Monocular depth estimation is vital for scene understanding and downstream tasks. We focus on the supervised setup, in which ground-truth depth is available only at training time. Based on knowledge about the high regularity of real 3D…

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose…

Accurate surround-view depth estimation provides a competitive alternative to laser-based sensors and is essential for 3D scene understanding in autonomous driving. While empirical studies have proposed various approaches that primarily…

Monocular depth estimation is an ill-posed problem as the same 2D image can be projected from infinite 3D scenes. Although the leading algorithms in this field have reported significant improvement, they are essentially geared to the…

Point cloud normal estimation is a fundamental task in 3D geometry processing. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This results in…

Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences. Moreover, it can be conveniently used in various applications, such as autonomous driving, robotics,…

We present a new approach to the problem of estimating the 3D room layout from a single panoramic image. We represent room layout as three 1D vectors that encode, at each image column, the boundary positions of floor-wall and ceiling-wall,…

Supervised learning depth estimation methods can achieve good performance when trained on high-quality ground-truth, like LiDAR data. However, LiDAR can only generate sparse 3D maps which causes losing information. Obtaining high-quality…

Monocular geometric scene understanding combines panoptic segmentation and self-supervised depth estimation, focusing on real-time application in autonomous vehicles. We introduce MGNiceNet, a unified approach that uses a linked kernel…