Related papers: Pix4Point: Image Pretrained Standard Transformers …

With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as…

Point clouds, being the simple and compact representation of surface geometry of 3D objects, have gained increasing popularity with the evolution of deep learning networks for classification and segmentation tasks. Unlike human, teaching…

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to…

In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compression. However, few…

Pre-training is crucial in 3D-related fields such as autonomous driving where point cloud annotation is costly and challenging. Many recent studies on point cloud pre-training, however, have overlooked the issue of incompleteness, where…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…

The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are generally sparse and of low density. These points clouds will…

Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space.…

Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional…

3D scene understanding from point clouds plays a vital role for various robotic applications. Unfortunately, current state-of-the-art methods use separate neural networks for different tasks like object detection or room layout estimation.…

Point cloud video perception has become an essential task for the realm of 3D vision. Current 4D representation learning techniques typically engage in iterative processing coupled with dense query operations. Although effective in…

Point cloud data now are popular data representations in a number of three-dimensional (3D) vision research realms. However, due to the limited performance of sensors and sensing noise, the raw data usually suffer from sparsity, noise, and…

The scale diversity of point cloud data presents significant challenges in developing unified representation learning techniques for 3D vision. Currently, there are few unified 3D models, and no existing pre-training method is equally…

Deep learning techniques for point clouds have achieved strong performance on a range of 3D vision tasks. However, it is costly to annotate large-scale point sets, making it critical to learn generalizable representations that can transfer…

Object reconstruction from 3D point clouds has been a long-standing research problem in computer vision and computer graphics, and achieved impressive progress. However, reconstruction from time-varying point clouds (a.k.a. 4D point clouds)…

3D object detection is a crucial research topic in computer vision, which usually uses 3D point clouds as input in conventional setups. Recently, there is a trend of leveraging multiple sources of input data, such as complementing the 3D…

Accurate 3D scene understanding in outdoor environments heavily relies on high-quality point clouds. However, LiDAR-scanned data often suffer from extreme sparsity, severely hindering downstream 3D perception tasks. Existing point cloud…

As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly…

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their…

Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid. However, unstructured data like 3D point clouds containing irregular neighborhoods constantly breaks…