相关论文: PLOT: Pseudo-Labeling via Video Object Tracking fo…

Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of…

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels,…

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g.,…

Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible. Most detectors consider each 3D object as an independent…

The labels of monocular 3D object detection (M3OD) are expensive to obtain. Meanwhile, there usually exists numerous unlabeled data in practical applications, and pre-training is an efficient way of exploiting the knowledge in unlabeled…

To ensure safe urban driving for autonomous platforms, it is crucial not only to develop high-performance object detection techniques but also to establish a diverse and representative dataset that captures various urban environments and…

A key contributor to recent progress in 3D detection from single images is monocular depth estimation. Existing methods focus on how to leverage depth explicitly, by generating pseudo-pointclouds or providing attention cues for image…

Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional…

Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human…

Despite significant progress in semi-supervised learning for image object detection, several key issues are yet to be addressed for video object detection: (1) Achieving good performance for supervised video object detection greatly depends…

3D object detection is one of the most important components in any Self-Driving stack, but current state-of-the-art (SOTA) lidar object detectors require costly & slow manual annotation of 3D bounding boxes to perform well. Recently,…

Compared to typical multi-sensor systems, monocular 3D object detection has attracted much attention due to its simple configuration. However, there is still a significant gap between LiDAR-based and monocular-based methods. In this paper,…

State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of…

Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance…

With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…

We present ONCE-3DLanes, a real-world autonomous driving dataset with lane layout annotation in 3D space. Conventional 2D lane detection from a monocular image yields poor performance of following planning and control tasks in autonomous…

We present an on-line 3D visual object tracking framework for monocular cameras by incorporating spatial knowledge and uncertainty from semantic mapping along with high frequency measurements from visual odometry. Using a combination of…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

The emerging trend in computer vision emphasizes developing universal models capable of simultaneously addressing multiple diverse tasks. Such universality typically requires joint training across multi-domain datasets to ensure effective…

Within the past decade, the rise of applications based on artificial intelligence (AI) in general and machine learning (ML) in specific has led to many significant contributions within different domains. The applications range from robotics…