Related papers: Simultaneous Diffusion Sampling for Conditional Li…

Recently, 3D generation methods have shown their powerful ability to automate 3D model creation. However, most 3D generation methods only rely on an input image or a text prompt to generate a 3D model, which lacks the control of each…

Lidar point cloud distortion from moving object is an important problem in autonomous driving, and recently becomes even more demanding with the emerging of newer lidars, which feature back-and-forth scanning patterns. Accurately estimating…

3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation. In this task, we notice that images could provide rich texture, color, and discriminative information, which can…

3D detection is a critical task that enables machines to identify and locate objects in three-dimensional space. It has a broad range of applications in several fields, including autonomous driving, robotics and augmented reality. Monocular…

Fast and efficient semantic segmentation of large-scale LiDAR point clouds is a fundamental problem in autonomous driving. To achieve this goal, the existing point-based methods mainly choose to adopt Random Sampling strategy to process…

Poles and building edges are frequently observable objects on urban roads, conveying reliable hints for various computer vision tasks. To repetitively extract them as features and perform association between discrete LiDAR frames for…

While generative world models have advanced video and occupancy-based data synthesis, LiDAR generation remains underexplored despite its importance for accurate 3D perception. Extending generation to 4D LiDAR data introduces challenges in…

We present a review of 3D point cloud processing and learning for autonomous driving. As one of the most important sensors in autonomous vehicles, light detection and ranging (LiDAR) sensors collect 3D point clouds that precisely record the…

Scene flow allows autonomous vehicles to reason about the arbitrary motion of multiple independent objects which is the key to long-term mobile autonomy. While estimating the scene flow from LiDAR has progressed recently, it remains largely…

Point-clouds are a popular choice for vision and graphics tasks due to their accurate shape description and direct acquisition from range-scanners. This demands the ability to synthesize and reconstruct high-quality point-clouds. Current…

3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity…

Large-scale 3D point clouds (LS3DPC) obtained by LiDAR scanners require huge storage space and transmission bandwidth due to a large amount of data. The existing methods of LS3DPC compression separately perform rule-based point sampling and…

In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i.e., images possess more semantic information while point clouds specialize in…

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…

Building LiDAR generative models holds promise as powerful data priors for restoration, scene manipulation, and scalable simulation in autonomous mobile robots. In recent years, approaches using diffusion models have emerged, significantly…

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…

Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation. This continues to be a significant area of interest with the rise of new state-of-the-art methods…

We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D Gaussian splats, and simultaneously builds a compressed…

The Gaussian diffusion model, initially designed for image generation, has recently been adapted for 3D point cloud generation. However, these adaptations have not fully considered the intrinsic geometric characteristics of 3D shapes,…

LiDAR sensors are a key modality for 3D perception, yet they are typically designed independently of downstream tasks such as point cloud registration. Conventional registration operates on pre-acquired datasets with fixed LiDAR…