Related papers: Gait Sequence Upsampling using Diffusion Models fo…

Diffusion models form an important class of generative models today, accounting for much of the state of the art in cutting edge AI research. While numerous extensions beyond image and video generation exist, few of such approaches address…

Upsampling LiDAR point clouds in autonomous driving scenarios remains a significant challenge due to the inherent sparsity and complex 3D structures of the data. Recent studies have attempted to address this problem by converting the…

The Diffusion Probabilistic Model (DPM) has recently gained popularity in the field of computer vision, thanks to its image generation applications, such as Imagen, Latent Diffusion Models, and Stable Diffusion, which have demonstrated…

In this paper, we introduce Cirrus, a new long-range bi-pattern LiDAR public dataset for autonomous driving tasks such as 3D object detection, critical to highway driving and timely decision making. Our platform is equipped with a…

Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to…

Novel view synthesis has evolved rapidly, advancing from Neural Radiance Fields to 3D Gaussian Splatting (3DGS), which offers real-time rendering and rapid training without compromising visual fidelity. However, 3DGS relies heavily on…

Estimating the pose of objects from images is a crucial task of 3D scene understanding, and recent approaches have shown promising results on very large benchmarks. However, these methods experience a significant performance drop when…

Novel view synthesis under sparse views has been a long-term important challenge in 3D reconstruction. Existing works mainly rely on introducing external semantic or depth priors to supervise the optimization of 3D representations. However,…

A key challenge for autonomous vehicles is to navigate in unseen dynamic environments. Separating moving objects from static ones is essential for navigation, pose estimation, and understanding how other traffic participants are likely to…

In this paper, we present a new self-supervised scene flow estimation approach for a pair of consecutive point clouds. The key idea of our approach is to represent discrete point clouds as continuous probability density functions using…

Diffusion models have emerged as powerful learned priors for solving inverse problems. However, current iterative solving approaches which alternate between diffusion sampling and data consistency steps typically require hundreds or…

Point-pixel registration between LiDAR point clouds and camera images is a fundamental yet challenging task in autonomous driving and robotic perception. A key difficulty lies in the modality gap between unstructured point clouds and…

Colored point cloud, which includes geometry and attribute components, is a mainstream representation enabling realistic and immersive 3D applications. To generate large-scale and denser colored point clouds, we propose a deep…

The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy. However, like classification models, segmentation models can be vulnerable to…

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for…

Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…

Data augmentation is widely used to train deep learning models to address data scarcity. However, traditional data augmentation (TDA) typically relies on simple geometric transformation, such as random rotation and rescaling, resulting in…

Bayesian models based on Gaussian processes (GPs) offer a flexible framework to predict spatially distributed variables with uncertainty. But the use of nonstationary priors, often necessary for capturing complex spatial patterns, makes…

In this paper, we developed the solution of roadside LiDAR object detection using a combination of two unsupervised learning algorithms. The 3D point clouds are firstly converted into spherical coordinates and filled into the…

Object-level mapping builds a 3D map of objects in a scene with detailed shapes and poses from multi-view sensor observations. Conventional methods struggle to build complete shapes and estimate accurate poses due to partial occlusions and…