3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to
become a mainstream method for 3D representations. It can effectively transform multi-view …

Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-
view captures restricts their broader applicability. In this work, we propose\textbf …

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of
complex videos from a text description. However, most existing models lack fine-grained …

As one of the most popular and sought-after generative models in the recent years, diffusion
models have sparked the interests of many researchers and steadily shown excellent …

Spectrograms are 2D representations of sound that look very different from the images found
in our visual world. And natural images, when played as spectrograms, make unnatural …

Advancements in 3D scene reconstruction have transformed 2D images from the real world
into 3D models, producing realistic 3D results from hundreds of input photos. Despite great …

We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes
parameterized by 3D Gaussians from\textit {unposed} sparse multi-view images. Our model …

Reconstructing and rendering 3D objects from highly sparse views is of critical importance
for promoting applications of 3D vision techniques and improving user experience …

Closed-loop simulation is essential for advancing end-to-end autonomous driving systems.
Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on …

Modern generative models demonstrate impressive capabilities, likely stemming from an
ability to identify and manipulate abstract concepts underlying their training data. However …