Reconstruction of a continuous surface of two-dimensional manifold from its raw, discrete
point cloud observation is a long-standing problem in computer vision and graphics …

Modern methods for vision-centric autonomous driving perception widely adopt the bird's-
eye-view (BEV) representation to describe a 3D scene. Despite its better efficiency than …

Rigorously testing autonomy systems is essential for making safe self-driving vehicles (SDV)
a reality. It requires one to generate safety critical scenarios beyond what can be collected …

Image super-resolution (SR) has attracted increasing attention due to its wide applications.
However, current SR methods generally suffer from over-smoothing and artifacts, and most …

Diffusion models have emerged as the state-of-the-art for image generation, among other
tasks. Here, we present an efficient diffusion-based model for 3D-aware generation of neural …

Emerging neural radiance fields (NeRF) are a promising scene representation for computer
graphics, enabling high-quality 3D reconstruction and novel view synthesis from image …

In this paper, we develop position embedding transformation (PETR) for multi-view 3D
object detection. PETR encodes the position information of 3D coordinates into image …

Neural graphics primitives, parameterized by fully connected neural networks, can be costly
to train and evaluate. We reduce this cost with a versatile new input encoding that permits …

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using
only collections of single-view 2D photographs has been a long-standing challenge …

Neural implicit representations have recently shown encouraging results in various
domains, including promising progress in simultaneous localization and map** (SLAM) …