方川
@JiangWenPL Hi, have you solved the problem? I found same problems when i finetune the pretrained model on iGibson dataset, the training loss is declining while the validation loss is...
same concern, looking forward answers
Well, I haved digged into this problem, one cue is that the equirect_depth_image seems been stitched by 6 cubemap perspective images. Then I generate 6 cubic faces from the equirect_depth_image...
> Hey @fangchuan, Haven't had time to dig into this. The PTex support is a separate code path and shader from any other asset support. I think you are on...
i have the same problem, i extract the zip file on the windows by 7zip, it told me some error occured in the head of file, but the file was...
@sytelus hi, i saw you push the latest binary on the v1.2.0 Linux, have you updated the CityEnvironment package? i think something wrong with this achive
> > Hi, thanks for your wonderful work! I'm trying to repeat the quantitative results in your paper on a single A100 GPU. I am able to generate the tsdf...
Same concerns. Furthermore, I also feel confused about how to get the real scale depth prediction from the approach mentioned in paper. By looking through the codes, it seems not...
Dear author, I finetune EscherNet (load the pretrained weights of 6DoF) on an indoor scene dataset which contains multiview images with known poses. By looking through the tensorflow/wandb monitor, the...
> Hi, it looks like an overfitting problem. How's the visualisation of the training split and the PSNR metrics on train/val splits? It makes sense that the more views are...