[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang
Here is the log from my terminal
ic| 'report'
ic| "Before prune iteration, number of gaussians: " + str(len(gaussians.get_xyz)): 'Before prune iteration, number of gaussians: 5319759'
Training progress: 86%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 30000/35000 [26:22<04:22, 19.04it/s, Loss=0.2463291]ic| import_score.shape: torch.Size([5319759])
ic| "After prune iteration, number of gaussians: " + str(len(gaussians.get_xyz)): 'After prune iteration, number of gaussians: 1'
Seems like the script was excuted but I got 1 point after the pruning. How can I solve the problem?
Dear Author:
Here is the log from my terminal ic| 'report' ic| "Before prune iteration, number of gaussians: " + str(len(gaussians.get_xyz)): 'Before prune iteration, number of gaussians: 5319759' Training progress: 86%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊ | 30000/35000 [26:22<04:22, 19.04it/s, Loss=0.2463291]ic| import_score.shape: torch.Size([5319759]) ic| "After prune iteration, number of gaussians: " + str(len(gaussians.get_xyz)): 'After prune iteration, number of gaussians: 1'
Seems like the script was excuted but I got 1 point after the pruning. How can I solve the problem?
Thank you!