Related papers: LiDARCrafter: Dynamic 4D World Modeling from LiDAR…

LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on spatial alignment between LiDAR and camera sensors, they often…

World models, especially in autonomous driving, are trending and drawing extensive attention due to their capacity for comprehending driving environments. The established world model holds immense potential for the generation of…

Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artifacts and temporal drift. We hypothesize that the view…

Generating 3D worlds from text is a highly anticipated goal in computer vision. Existing works are limited by the degree of exploration they allow inside of a scene, i.e., produce streched-out and noisy artifacts when moving beyond central…

Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily…

LiDAR provides accurate geometric measurements of the 3D world. Unfortunately, dense LiDARs are very expensive and the point clouds captured by low-beam LiDAR are often sparse. To address these issues, we present UltraLiDAR, a data-driven…

Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet they remain constrained by scarce annotated real-world V2X driving datasets and limited…

3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid…

World models aim to endow AI systems with the ability to represent, generate, and interact with dynamic environments in a coherent and temporally consistent manner. While recent video generation models have demonstrated impressive visual…

Deep learning models for self-driving cars require a diverse training dataset to manage critical driving scenarios on public roads safely. This includes having data from divergent trajectories, such as the oncoming traffic lane or…

Building models capable of generating structured output is a key challenge for AI and robotics. While generative models have been explored on many types of data, little work has been done on synthesizing lidar scans, which play a key role…

Generative artificial intelligence has recently progressed from static image and video synthesis to 3D content generation, culminating in the emergence of 4D generation-the task of synthesizing temporally coherent dynamic 3D assets guided…

The synthesis of spatiotemporally coherent 4D content presents fundamental challenges in computer vision, requiring simultaneous modeling of high-fidelity spatial representations and physically plausible temporal dynamics. Current…

Autonomous driving demands high-quality LiDAR data, yet the cost of physical LiDAR sensors presents a significant scaling-up challenge. While recent efforts have explored deep generative models to address this issue, they often consume…

Generating realistic 3D indoor scenes from user inputs remains a challenging problem in computer vision and graphics, requiring careful balance of geometric consistency, spatial relationships, and visual realism. While neural generation…

Evaluating and training autonomous driving systems require diverse and scalable corner cases. However, most existing scene generation methods lack controllability, accuracy, and versatility, resulting in unsatisfactory generation results.…

There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR…

Text-to-LiDAR generation can customize 3D data with rich structures and diverse scenes for downstream tasks. However, the scarcity of Text-LiDAR pairs often causes insufficient training priors, generating overly smooth 3D scenes. Moreover,…

LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a…

Within a perception framework for autonomous mobile and robotic systems, semantic analysis of 3D point clouds typically generated by LiDARs is key to numerous applications, such as object detection and recognition, and scene reconstruction.…