Tatsuya Yatagawa
Tatsuya Yatagawa
Now I have added "torch" as a requirement. If your system already have torch installed, then, I think CUDA-enabled library will be installed 👍
For reference, I consumed about 22GB memory by Fusibile for processing Francis, Lighthouse and some other image sets in Tanks and Temples.
Hi @TruongKhang, I tested both the fusibile and python fusion. As far as I tested, the amount of noise is a bit less by python fusion than by fusibile. I...
Hi @TruongKhang, Thank you for sharing your knowledge. Yes, I got almost the same results as those you got. I used the short depth range provided by the MVSNet repo,...
Fixed by v0.2.2.
Hi @LeroyR, thanks for your pull request. Before merging, I would like to ask you why you need to decrease the near clip distance. According to my experience, the huge...
Hi @MD-Lai, Thanks for your interest in my project. Since this is my voluntary project, I am afraid I cannot fulfill all your requests due to the lack of time....
Fixed by #19.
For who sees this issue page, I solved the above problem with the code like the following. ```python camera = pycolmap.Camera( model=camera_type, width=image_size[0], height=image_size[1], params=pycolmap_intri, camera_id=fidx + 1 ) reconstruction.add_camera(camera)...