gwxxx
gwxxx
> I don't understand what you want to do. Can you be specific about what you are trying to accomplish? I have used colmap to calibrate 30 cameras. However, some...
> I am still not sure what the issue is. Why not take more images and run a reconstruction again (potentially starting from the old parameters)? It takes much time...
> [@xxnz](https://github.com/xxnz) > > According to [#376 (comment)](https://github.com/graphdeco-inria/gaussian-splatting/issues/376#issuecomment-1774659203) and [#388 (comment)](https://github.com/graphdeco-inria/gaussian-splatting/issues/388#issuecomment-1779584669), the author mentioned that they do not use the normalized depth. So `znear` and `zfar` take no effect in...
> The FPS in Table 1 represents the inference time of the entire feed-forward network, including feature encoding, decoding and rendering time. Thanks for your reply! So in Table 3,...
> Yes, because for the per-scene optimization (Table 3), we discard the network part and only need to optimize the Gaussian point cloud, in which case the FPS is the...
> The pre-trained generalizable model provides a point cloud as the initialization of 3DGS (per-scene optimization). Like 3DGS, we only optimize the 3D Gaussians, not the feed-forward network. So for...
> Yes, you are right！ Thanks！another question is why only use 2 or 3 images for the first pipeline? Is it because using all images will get a much lower...
> A lot of images as input will definitely slow down the FPS. Actually, our method mainly focuses on sparse (few-shot) view reconstruction. Can I use this pipeline: input all...
> I think that's a great idea! You can try it. If you encounter any questions in the future, feel free to contact us. Thank you!
I want to ask about use custom data to render new views. The resolution of my data is 3840*2160, so should I change the resolution in colmap_eval.yaml?