We introduce Lumiere–a text-to-video diffusion model designed for synthesizing videos that
portray realistic, diverse and coherent motion–a pivotal challenge in video synthesis. To this …

We introduce GRM, a large-scale reconstructor capable of recovering a 3D asset from
sparse-view images in around 0.1 s. GRM is a feed-forward transformer-based model that …

Diffusion models, a powerful and universal generative artificial intelligence technology, have
achieved tremendous success and opened up new possibilities in diverse applications. In …

Despite recent advances in text-to-3D generative methods there is a notable absence of
reliable evaluation metrics. Existing metrics usually focus on a single criterion each such as …

In the realm of digital creativity, our potential to craft intricate 3D worlds from imagination is
often hampered by the limitations of existing digital tools, which demand extensive expertise …

Recent breakthroughs in text-to-4D generation rely on pre-trained text-to-image and text-to-
video models to generate dynamic 3D scenes. However current text-to-4D methods face a …

Abstract 3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at
rendering photorealistic novel views of complex scenes. However recovering a high-quality …

We propose\textbf {DMV3D}, a novel 3D generation approach that uses a transformer-based
3D large reconstruction model to denoise multi-view diffusion. Our reconstruction model …

Abstract We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality
human motion generation. Current state-of-the-art generative diffusion models have …

The rapid development of diffusion models (DMs) has significantly advanced image and
video applications, making" what you want is what you see" a reality. Among these, video …