Related papers: DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3…
Joint object detection and semantic segmentation can be applied to many fields, such as self-driving cars and unmanned surface vessels. An initial and important progress towards this goal has been achieved by simply sharing the deep…
Monocular depth estimation aims to recover the depth information of 3D scenes from 2D images. Recent work has made significant progress, but its reliance on large-scale datasets and complex decoders has limited its efficiency and…
Although deep neural networks have been widely applied to computer vision problems, extending them into multiview depth estimation is non-trivial. In this paper, we present MVDepthNet, a convolutional network to solve the depth estimation…
In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural…
The main challenge of monocular 3D object detection is the accurate localization of 3D center. Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose…
Despite receiving significant attention from the research community, the task of segmenting and tracking objects in monocular videos still has much room for improvement. Existing works have simultaneously justified the efficacy of dilated…
Deep neural networks (DNNs) have shown remarkable performance improvements on vision-related tasks such as object detection or image segmentation. Despite their success, they generally lack the understanding of 3D objects which form the…
Vision-based stair perception can help autonomous mobile robots deal with the challenge of climbing stairs, especially in unfamiliar environments. To address the problem that current monocular vision methods are difficult to model stairs…
In this work, we propose a novel single-shot and keypoints-based framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design a fully convolutional model to predict object keypoints, dimension, and…
State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D…
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to convolutions as a plug-and-play module and embed them in…
Image anomaly detection problems aim to determine whether an image is abnormal, and to detect anomalous areas. These methods are actively used in various fields such as manufacturing, medical care, and intelligent information.…
Recently, Transformer networks have achieved impressive results on a variety of vision tasks. However, most of them are computationally expensive and not suitable for real-world mobile applications. In this work, we present Mobile…
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image…
Deep Learning based techniques have been adopted with precision to solve a lot of standard computer vision problems, some of which are image classification, object detection and segmentation. Despite the widespread success of these…
Incomplete point clouds captured by 3D sensors often result in the loss of both geometric and semantic information. Most existing point cloud completion methods are built on rotation-variant frameworks trained with data in canonical poses,…
Existing deep learning-based approaches for monocular 3D object detection in autonomous driving often model the object as a rotated 3D cuboid while the object's geometric shape has been ignored. In this work, we propose an approach for…
Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…
Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state…
In this paper, we propose a learning-based method for predicting dense depth values of a scene from a monocular omnidirectional image. An omnidirectional image has a full field-of-view, providing much more complete descriptions of the scene…