Related papers: Quasi-Balanced Self-Training on Noise-Aware Synthe…

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data…

Recent progress of semantic point clouds analysis is largely driven by synthetic data (e.g., the ModelNet and the ShapeNet), which are typically complete, well-aligned and noisy free. Therefore, representations of those ideal synthetic…

Earlier work demonstrates the promise of deep-learning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful. To this end, we introduce a new model SqueezeSegV2 that is more…

Deep-learning models for 3D point cloud semantic segmentation exhibit limited generalization capabilities when trained and tested on data captured with different sensors or in varying environments due to domain shift. Domain adaptation…

Unlike image or text domains that benefit from an abundance of large-scale datasets, point cloud learning techniques frequently encounter limitations due to the scarcity of extensive datasets. To overcome this limitation, we present…

LiDAR object detection algorithms based on neural networks for autonomous driving require large amounts of data for training, validation, and testing. As real-world data collection and labeling are time-consuming and expensive,…

Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact…

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real…

Point cloud registration is to estimate a transformation to align point clouds collected in different perspectives. In learning-based point cloud registration, a robust descriptor is vital for high-accuracy registration. However, most…

Semantic segmentation in 3D indoor scenes has achieved remarkable performance under the supervision of large-scale annotated data. However, previous works rely on the assumption that the training and testing data are of the same…

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works…

Knowledge transfer from synthetic to real data has been widely studied to mitigate data annotation constraints in various computer vision tasks such as semantic segmentation. However, the study focused on 2D images and its counterpart in 3D…

Owing to the typical long-tail data distribution issues, simulating domain-gap-free synthetic data is crucial in robotics, photogrammetry, and computer vision research. The fundamental challenge pertains to credibly measuring the difference…

The task of point cloud upsampling aims to acquire dense and uniform point sets from sparse and irregular point sets. Although significant progress has been made with deep learning models, state-of-the-art methods require ground-truth dense…

Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current learning methods based on the clean label assumptions may fail with noisy labels. Yet, class…

Judging the quality of samples synthesized by generative models can be tedious and time consuming, especially for complex data structures, such as point clouds. This paper presents a novel approach to quantify the realism of local regions…

Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is time-consuming and challenging. While synthetically…

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…

Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an important role in…

In the practical application of point cloud completion tasks, real data quality is usually much worse than the CAD datasets used for training. A small amount of noisy data will usually significantly impact the overall system's accuracy. In…