Learningm
Learningm
> I haven't checked the code in detail, but I assume they just make the poses "a tiny bit" smaller than the unit sphere, to be safe. I don't think...
> > > From your video, it would seem your problem could be related to inaccurate poses. Have you tried to put some nice features on the table (stickers, QRcodes,...
> @Learningm @povolann sorry to bother you. I also encountered lots of floaters when training on my custom data. I tried the parameters you mentioned above, they help, but still...
@Wuziyi616 I got blurry edge problem as the video posted above and it seems hard to solve through tuning parameters. Did you get some good results without the blurry problem...
@Wuziyi616 Your result looks good. I got similar result after tuning the parameters mentioned above.
@Wuziyi616 Cool! Thanks for sharing.
Did you figure out how to debug?
Hi, did you resolve the 'floaters' problem? I met the same issue, so many floaters.
Got it. It seems necessary for debugging on the Neural Point Catacaustics dataset myself. Thanks.
@wukailu ,Hi, I want to ask some details about training controlnet-tile. I tried to re-implement it using diffusers, finetuning the tile model, tiling 4-views to a sheet. Data processing details:...