Related papers: MeshFleet: Filtered and Annotated 3D Vehicle Datas…

Data annotation is crucial for developing machine learning solutions. The current paradigm is to hire ordinary human annotators to annotate data instructed by expert-crafted guidelines. As this paradigm is laborious, tedious, and costly, we…

ResNet has achieved tremendous success in computer vision through its residual connection mechanism. ResNet can be viewed as a discretized form of ordinary differential equations (ODEs). From this perspective, the multiple residual blocks…

Advanced Driver-Assistance Systems (ADAS) have successfully integrated learning-based techniques into vehicle perception and decision-making. However, their application in 3D lane detection for effective driving environment perception is…

Significant progress has been made in training large generative models for natural language and images. Yet, the advancement of 3D generative models is hindered by their substantial resource demands for training, along with inefficient,…

Three-dimensional (3D) objects have wide applications. Despite the growing interest in 3D modeling in academia and industries, designing and/or creating 3D objects from scratch remains time-consuming and challenging. With the development of…

Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…

This report presents the design and implementation of a semi-automated data annotation pipeline developed within the DARTS project, whose goal is to create a large-scale, multimodal dataset of driving scenarios recorded in Polish…

The field of generative AI has a transformative impact on various areas, including virtual reality, autonomous driving, the metaverse, gaming, and robotics. Among these applications, 3D object generation techniques are of utmost importance.…

In vision-and-language navigation (VLN), an embodied agent is required to navigate in realistic 3D environments following natural language instructions. One major bottleneck for existing VLN approaches is the lack of sufficient training…

Deep learning in medical imaging is often limited by scarce and imbalanced annotated data. We present SSGNet, a unified framework that combines class specific generative modeling with iterative semisupervised pseudo labeling to enhance both…

Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks have not seen the same progress, in part due to the challenges…

Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. In this paper, we extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation…

As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident. In our work, we aim to train…

Humans intuitively perceive object shape and orientation from a single image, guided by strong priors about canonical poses. However, existing 3D generative models often produce misaligned results due to inconsistent training data, limiting…

Data collection for autonomous driving is rapidly accelerating, but manual annotation, especially for 3D labels, remains a major bottleneck due to its high cost and labor intensity. Autolabeling has emerged as a scalable alternative,…

Maintaining high data quality is crucial for reliable data analysis and machine learning (ML). However, existing data quality management tools often lack automation, interactivity, and integration with ML workflows. This demonstration paper…

Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information. In this work, we introduce a new large-scale dataset that consists of 409 fine-grained categories and 31,881 images…

Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models…

Dense and versatile image representations underpin the success of virtually all computer vision applications. However, state-of-the-art networks, such as transformers, produce low-resolution feature grids, which are suboptimal for dense…

Closed-set 3D perception models trained on only a pre-defined set of object categories can be inadequate for safety critical applications such as autonomous driving where new object types can be encountered after deployment. In this paper,…