fanzz1208

我下载的官方shanghaitech这个数据集都是视频片段没有抽帧，这个虽然可以自己抽，但是测试集的标签文件，也就是那个.mat文件我不知道去哪里获取

ave you resolved the issue of installing ColmapForVisSat?

I have modify the CUDA rasterization according to https://github.com/graphdeco-inria/diff-gaussian-rasterization/pull/5/files but error: Training progress: 0%| | 0/30000 [00:00

> Hi @fanzz1208, Scaffold-GS employs a customized rasterization pipeline that adds visible_filter to per-filter the visible Gaussians. It can reduce the number of Gaussians to inference MLPs. This pipeline (https://github.com/graphdeco-inria/diff-gaussian-rasterization/pull/5/files)...

> to give a rand init during loading data So what should I do, just delete points3D.txt from the dataset? Or, how can I modify this code? my dataset is...

> To do so, you can replace > > https://github.com/city-super/Scaffold-GS/blob/da97ef8257b46d51c432df0df8b62f7c3a3c1079/scene/dataset_readers.py#L191-L194 > > with > ``` > num_pts = 100_000 > print(f"Generating random point cloud ({num_pts})...") > xyz = np.random.random((num_pts, 3))...