Open lazyDamon opened 1 year ago
Hello. Since the sparseneus is only trained on the DTU, which is relatively small dataset and may have domain gap with your data. To prepare a custom dataset, you should first rescale the object of the interest into a unit sphere (-0.5, 0.5), and get its multiple images with camera intrinsics extrinsics.
I tried converting my data to DTU format by Neushttps://github.com/Totoro97/NeuS/tree/main/preprocess_custom_data. Then I run SparseNeus, but result is bad. In the same way, it is no problem with using data for other projects.
Hi there, Can you provide a detailed explanation on how to create a custom dataset for training Sparseneus? I have a collection of images along with their corresponding camera intrinsics and extrinsics. Thanks!!
I tried converting my data to DTU format by Neushttps://github.com/Totoro97/NeuS/tree/main/preprocess_custom_data. Then I run SparseNeus, but result is bad. In the same way, it is no problem with using data for other projects.
Hi, I ran into the same problem. Do you have any ideas to solve it? Thanks!
Hi, thank for your great work! I tried to inference on my own data, but result was very bad. Can you tell me how to prepare my data? I have extrinsics and intrinsics by colmap.