There has been an emerging paradigm shift from the era of “internet AI” to “embodied AI,”
where AI algorithms and agents no longer learn from datasets of images, videos or text …

Recently, DreamFusion demonstrated the utility of a pretrained text-to-image diffusion model
to optimize Neural Radiance Fields (NeRF), achieving remarkable text-to-3D synthesis …

As several industries are moving towards modeling massive 3D virtual worlds, the need for
content creation tools that can scale in terms of the quantity, quality, and diversity of 3D …

Denoising diffusion models (DDMs) have shown promising results in 3D point cloud
synthesis. To advance 3D DDMs and make them useful for digital artists, we require (i) high …

Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of
large-scale real-scanned 3D databases. To facilitate the development of 3D perception …

We extend neural radiance fields (NeRFs) to dynamic large-scale urban scenes. Prior work
tends to reconstruct single video clips of short durations (up to 10 seconds). Two reasons …

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

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 …

Abstract Neural Radiance Fields (NeRF) have emerged as a powerful representation for the
task of novel view synthesis due to their simplicity and state-of-the-art performance. Though …

We observe that despite their hierarchical convolutional nature, the synthesis process of
typical generative adversarial networks depends on absolute pixel coordinates in an …