LaFeuilleMorte

Got the same problem, the pollevent function seemed to be working well when only one window was created. But when another was created, whatever happened on the window will affect...

I've tried reconstruction from images of which the backgrounds has been segmented (Only the foreground object), Unfortunately the model performed poorly on such cases. Maybe the object itself has too...

> # output['pred1']['conf'] *= my_foreground_mask_view1.float() # mask is 0 on background and 1 on foreground > # output['pred2']['conf'] *= my_foreground_mask_view2.float() # mask is 0 on background and 1 on foreground...

老哥，可以分享一下train code吗，我的邮箱是[email protected]。感谢

No, I print the device which the model will be sent, it's GPU. My computer is RTX 3090 + torch 2.2.1 + cuda 11.8 

You can try to use this algo https://github.com/Jumpat/SegAnyGAussians to seg gaussian point clouds before you use sugar to extract mesh.

Hi, Thanks for the reply Do you have the laptop or desktop version of the RTX 3090? It's a desktop one. How much memory does it have? 24GB How many...

> 我的屌丝配置计算机： My poor-configuration computer: > > (2016，personal GPU workstation） GPU： Titan-XP 12G GPU-memory CPU： 12 cores MEM: 32G DISK: SSD > > the training speed is acceptable，15000 iterations, about...

> Thanks for your brilliant work, I was trying to crop an object out of a scene and remove all its background. Is it able to do this? Thanks in...

> @hxy-123 @DX3906G I set imd_pair_Strategy to sequential in dfsfm.yaml（ img_pair_strategy: sequential #exhaustive sequential)， It will report an error: (eval_core_ray_wrapper pid=888415) 2024-07-15 10:49:06.431 | ERROR | **main**:eval_core_ray_wrapper:93 - Error captured:...