Related papers: 4D-RaDiff: Latent Diffusion for 4D Radar Point Clo…
In the past few years we have seen great advances in object perception (particularly in 4D space-time dimensions) thanks to deep learning methods. However, they typically rely on large amounts of high-quality labels to achieve good…
Labeling LiDAR point clouds for training autonomous driving is extremely expensive and difficult. LiDAR simulation aims at generating realistic LiDAR data with labels for training and verifying self-driving algorithms more efficiently.…
4-dimensional (4D) radar is increasingly adopted in autonomous driving for perception tasks, owing to its robustness under adverse weather conditions. To better utilize the spatial information inherent in 4D radar data, recent deep learning…
Recent multimodal fusion methods, integrating images with LiDAR point clouds, have shown promise in scene flow estimation. However, the fusion of 4D millimeter wave radar and LiDAR remains unexplored. Unlike LiDAR, radar is cheaper, more…
Training autonomous driving and navigation systems requires large and diverse point cloud datasets that capture complex edge case scenarios from various dynamic urban settings. Acquiring such diverse scenarios from real-world point cloud…
Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and…
In four-dimensional (4D) Radar-based point cloud generation, clutter removal is commonly performed using the constant false alarm rate (CFAR) algorithm. However, CFAR may not fully capture the spatial characteristics of objects. To address…
The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled.…
Predicting how the world can evolve in the future is crucial for motion planning in autonomous systems. Classical methods are limited because they rely on costly human annotations in the form of semantic class labels, bounding boxes, and…
While consumer displays increasingly support more than 10 stops of dynamic range, most image assets such as internet photographs and generative AI content remain limited to 8-bit low dynamic range (LDR), constraining their utility across…
Robust 3D object detection in adverse weather is highly challenging due to the varying reliability of different sensors. While existing LiDAR-4D radar fusion methods improve robustness, they predominantly rely on fixed or weakly adaptive…
We present LidarDM, a novel LiDAR generative model capable of producing realistic, layout-aware, physically plausible, and temporally coherent LiDAR videos. LidarDM stands out with two unprecedented capabilities in LiDAR generative…
High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion (LWD), a…
Mobile autonomy relies on the precise perception of dynamic environments. Robustly tracking moving objects in 3D world thus plays a pivotal role for applications like trajectory prediction, obstacle avoidance, and path planning. While most…
The burgeoning field of camouflaged object detection (COD) seeks to identify objects that blend into their surroundings. Despite the impressive performance of recent models, we have identified a limitation in their robustness, where…
Object detection in radar imagery with neural networks shows great potential for improving autonomous driving. However, obtaining annotated datasets from real radar images, crucial for training these networks, is challenging, especially in…
LiDAR scenes constitute a fundamental source for several autonomous driving applications. Despite the existence of several datasets, scenes from adverse weather conditions are rarely available. This limits the robustness of downstream…
A comprehensive understanding of 3D scenes is essential for autonomous vehicles (AVs), and among various perception tasks, occupancy estimation plays a central role by providing a general representation of drivable and occupied space.…
The search for refining 3D LiDAR data has attracted growing interest motivated by recent techniques such as supervised learning or generative model-based methods. Existing approaches have shown the possibilities for using diffusion models…
Integrated sensing and communications is a key enabler for the 6G wireless communication systems. The multiple sensing modalities will allow the base station to have a more accurate representation of the environment, leading to…