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
Little italian town, hand-painted style
army Jacket, 3D scan
Katana, blender
military Mech, future, scifi
A see no evil monkey on a kick drum
motorcycle, scifi, blender
Mr Bean Cartoon doing a T Pose
A DSLR photo of Sydney Opera House
a DSLR photo of a peacock on a surfboard
A pig wearing a back pack
@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},
}