Related papers: PVT-SSD: Single-Stage 3D Object Detector with Poin…

Monocular 3D scene understanding tasks, such as object size estimation, heading angle estimation and 3D localization, is challenging. Successful modern day methods for 3D scene understanding require the use of a 3D sensor. On the other…

Learning 3D point sets with rotational invariance is an important and challenging problem in machine learning. Through rotational invariant architectures, 3D point cloud neural networks are relieved from requiring a canonical global pose…

Single stage deep learning algorithm for 2D object detection was made popular by Single Shot MultiBox Detector (SSD) and it was heavily adopted in several embedded applications. PointPillars is a state of the art 3D object detection…

This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to…

Cross-modality registration between 2D images from cameras and 3D point clouds from LiDARs is a crucial task in computer vision and robotic. Previous methods estimate 2D-3D correspondences by matching point and pixel patterns learned by…

A fundamental challenge in point cloud object detection lies in the conflict between the extreme sparsity of distant points and the need for remote context understanding. The existing methods typically use 1D serialization to expand the…

In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in the current search point cloud given a template point cloud. Motivated by the success of transformers, we propose Point Tracking…

Learning object-centric representations from unsupervised videos is challenging. Unlike most previous approaches that focus on decomposing 2D images, we present a 3D generative model named DynaVol-S for dynamic scenes that enables…

3D single object tracking is a key task in 3D computer vision. However, the sparsity of point clouds makes it difficult to compute the similarity and locate the object, posing big challenges to the 3D tracker. Previous works tried to solve…

Existing visual change detectors usually adopt CNNs or Transformers for feature representation learning and focus on learning effective representation for the changed regions between images. Although good performance can be obtained by…

Monocular 3D object detection poses a significant challenge in 3D scene understanding due to its inherently ill-posed nature in monocular depth estimation. Existing methods heavily rely on supervised learning using abundant 3D labels,…

Wide-range and fine-grained vehicle detection plays a critical role in enabling active safety features in intelligent driving systems. However, existing vehicle detection methods based on rectangular bounding boxes (BBox) often struggle…

Existing point cloud based 3D detectors are designed for the particular scene, either indoor or outdoor ones. Because of the substantial differences in object distribution and point density within point clouds collected from various…

In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and…

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is…

The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction. We propose a new algorithm for…

While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds. Existing methods attempt to overcome this issue by…

Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several…

3D vehicle detection based on point cloud is a challenging task in real-world applications such as autonomous driving. Despite significant progress has been made, we observe two aspects to be further improved. First, the semantic context…

We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Computation speed is critical as detection is a necessary component for safety. Existing approaches are, however, expensive in…