Zhengyi Wang

是的他们是同时训练的，他们之间的关系在于他们的渲染图片同时被用来训练变分分布的score

Thank you for your interest in our work! The factor of VSD loss and LoRA loss does not matter, since they optimize different parameters. To balance these two loss, setting...

How about the results with rgb? The this is the video of textureless result.

(1) The `lambda_entropy` is a critical parameter. How about setting --lambda_entropy 10? (2) This prompt may be too hard for stable diffusion, maybe you can try `a pineapple` first and...

In general, complex prompts require a more careful choice of the parameters. It is possible that this may be generated by adjusting the parameters or even by adding new regularization...

Hi MrForExample, we will start to upload the training code of MVDiffusion in October

Hi MrForExample, the training code has been uploaded

Thank you for your interest in our work！ You're correct that Variational Autoencoders (VAEs) often struggle with precise reconstruction, leading to minor numerical disturbances in the outputs. To address this,...

Thank you for your response!

Thank you for your suggestion. I will fix this.