Abstract Neural Radiance Field (NeRF) significantly degrades when only a limited number
of views are available. To complement the lack of 3D information, depth-based models, such …

We present a method for text-driven perpetual view generation--synthesizing long-term
videos of various scenes solely, given an input text prompt describing the scene and camera …

Recent years have witnessed remarkable advances in artificial intelligence generated
content (AIGC), with diverse input modalities, eg, text, image, video, audio and 3D. The 3D is …

Abstract 3D city generation is a desirable yet challenging task since humans are more
sensitive to structural distortions in urban environments. Additionally generating 3D cities is …

Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which
constructs and renders an unconstrainedly large and 3D-grounded environment from …

Recent breakthroughs in text-guided image generation have led to remarkable progress in
the field of 3D synthesis from text. By optimizing neural radiance fields (NeRF) directly from …

We present PrimDiffusion, the first diffusion-based framework for 3D human generation.
Devising diffusion models for 3D human generation is difficult due to the intensive …

In this work, we introduce CC3D, a conditional generative model that synthesizes complex
3D scenes conditioned on 2D semantic scene layouts, trained using single-view images …

Despite increasingly realistic image quality, recent 3D image generative models often
operate on 3D volumes of fixed extent with limited camera motions. We investigate the task …

We present XCube a novel generative model for high-resolution sparse 3D voxel grids with
arbitrary attributes. Our model can generate millions of voxels with a finest effective …