daaixianzun

Results 5 issues of daaixianzun

Hello, thanks for your work! I tried to reproduce the work, and I ran the 'plane' category, the final CD as the pic shows ![cds](https://github.com/kimren227/CSGStumpNet/assets/67455751/7ee4fc4e-cf30-4e6e-bb93-0b67db286478) It is different form the...

抱歉再次打扰,上次询问您嘞SH2RGB的问题。近期我试了一下效果,但是转换结果和您论文中的有差距,请问是不是哪里处理不对? ![paper](https://github.com/Jumpat/SegAnyGAussians/assets/67455751/f7d2351b-2aa0-4b78-966d-039935d493b1) 对于这个场景,我读取了ply里的f_dc_0,f_dc_1,f_dc_2,将其传入了SH2RGB函数,结果作为rgb存入ply,最终用Viewer可视结果如下: ![viewer_room](https://github.com/Jumpat/SegAnyGAussians/assets/67455751/fc3572ec-8386-4a67-82d5-b3cce5cbe1ef) cloud_compare结果为: ![image](https://github.com/Jumpat/SegAnyGAussians/assets/67455751/97c59bd4-5934-499c-9fd3-c064deaa8d53)

您好,我在使用nerf_Synthetic数据集训练Gaussian时遇到了这个问题 RuntimeError: Function _RasterizeGaussiansBackward returned an invalid gradient at index 2 - got [0, 0, 3] but expected shape compatible with [0, 16, 3]。 我在Gaussian splatting的issues里找了一下没有具体解决措施,请问您有遇到过并解决吗?

Hello, thank you very much for your work. I would like to ask, after obtaining the Gaussian model, how to render a perspective different from the pose of the photo...

Thank you very much for your work, I recently had problems reproducing SA3D-GS. After executing train_seg.py the execution gave the command 'python render.py -m --target scene --segment', I've noticed that...