4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

Sherwin Bahmani; Ivan Skorokhodov; Victor Rong; Gordon Wetzstein; Leonidas J. Guibas; Peter Wonka; Sergey Tulyakov; Jeong Joon Park; Andrea Tagliasacchi; David B. Lindell

doi:10.1109/cvpr52733.2024.00764

CVPR2024顶会

4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

Sherwin Bahmani, Ivan Skorokhodov, Victor Rong, Gordon Wetzstein, Leonidas J. Guibas, Peter Wonka, Sergey Tulyakov, Jeong Joon Park, Andrea Tagliasacchi, David B. Lindell

DOI 出版方

2024年份

3顶会引用

摘要

7 SFU 8 Google "a space shuttle launching" "a crocodile playing a drum set" time viewpoint Figure 1. Text-to-4D Synthesis. We present 4D-fy, a technique that synthesizes 4D (i.e., dynamic 3D) scenes from a text prompt. We show scenes generated from two text prompts for different viewpoints (vertical dimension) at different time steps (horizontal dimension). Video results can be viewed on our website: https://sherwinbahmani.github.io/4dfy .