We use the threestudio implementation for all the baselines. A fixed configuration is used for each method (including ours) without prompt-wise hyperparameter tuning. The results here are without cherry picking.
Dreamfusion-IF
Magic3D-IF-SD
Text2Mesh-IF
ProlificDreamer
Ours
Flying Dragon, highly detailed, breathing fire
A bald eagle carved out of wood
Pedestal Fan (White)
a DSLR photo of a frog wearing a sweater
a DSLR photo of a ghost eating a hamburger
mecha vampire girl chibi
A 3D scan of AK47, weapon
Darth Vader helmet,g highly detailed
A photo of a horse walking
Fisherman House, cute, cartoon, blender, stylized
@article{shi2023MVDream,
author = {Shi, Yichun and Wang, Peng and Ye, Jianglong and Mai, Long and Li, Kejie and Yang, Xiao},
title = {MVDream: Multi-view Diffusion for 3D Generation},
journal = {arXiv:2308.16512},
year = {2023},
}