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 …
H Xie, Z Chen, F Hong, Z Liu - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
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 …
X Ren, J Huang, X Zeng, K Museth… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …