Jiazhong Cen
Jiazhong Cen
你好，这可能是由于view.image_height，view.feature_height没有和降采样后的图像对其的原因，导致原来输入进去的点的坐标都被映射到了地板上。可以检查下这两个变量。
Hi, I wonder what kind of noise you want to get rid of. There are some floaters in the space due to the inherent defect of 3D-GS. And there may...
You may need to change the code in lib/render_utils.py. [Here](https://github.com/Jumpat/SegmentAnythingin3D/blob/b25698cbc7ca8e71b73749685b36f2914d6cbee7/lib/render_utils.py#L165), we convert the depth to colormap. You can save the original depth directly rather than converting it.
How to understand 'aligned'? Theoretically they should be. However, the depth is estimated by NeRF, which may not align with the actual situation. But it should align with the rendered...
> Aligned: Each pixel in RGB corresponds one-to-one to each pixel in the depth map. If they are aligned, I can detect the object in RGB and combine it with...
> The NeRF you use is TensoRF, how can I change it to other models? In this codebase it is hard to change it, but I have integrated it with...
> I found that after running run.py, there are 120 rendered images. Where are these camera poses saved (rotation and translation matrices)? We did not save this trace. But you...
你好，请检查下self.grid的尺寸，并检查self.grid的创建，这可能是由于空间尺寸（长宽高）过于不均衡导致的，你的数据集colmap匹配能够顺利进行吗，匹配后得到的点云能够成功可视化吗？
你好，我们提供这一接口只是为了方便使用，和方法本身并无关系，实际上可以使用预训练的参数。但要注意的是该预训练模型对应的数据集以及其中图像的相机位姿必须保持一致。
对，其中需要用到mask变量来对分割结果进行可微渲染。应该是不同cuda版本对于变量类型的兼容性不同。