Downloads · 30 days
0
whitneysheng/pxl-20260505-30000-splat
pxl-20260505-30000-splat is a machine learning model from whitneysheng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
This repository contains the 30,000-iteration Gaussian Splat training output for pxl20260505230422914.
Downloads · 30 days
0
Access
Public
Updated May 7, 2026
Repo size
307 MB
Likes
0
Public
Click a slice to open those files.
.ply154 MB · 50%
From the Hugging Face model README
This repository contains the 30,000-iteration Gaussian Splat training output for pxl_20260505_230422914.
chkpnt30000.pth: training checkpoint at iteration 30000.point_cloud/iteration_30000/point_cloud.ply: exported point cloud at iteration 30000.point_cloud/iteration_30000/point_cloud_apparition_scale2p5_opacity0p3.ply: edited/exported point cloud variant.cameras.json: camera metadata from the training run.exposure.json: exposure metadata from the training run.cfg_args: training configuration arguments.input.ply: initial input point cloud.Namespace(sh_degree=3, source_path='/home/whitney/experimentation/datasets/pxl_20260505_230422914', model_path='datasets/pxl_20260505_230422914/trained_splat', images='images', depths='', resolution=-1, white_background=False, train_test_exp=False, data_device='cpu', eval=False)