Is there anybody who was able to get results with Colmap-free Gaussian Object

[TXSevenXT]

No for the moment sadly (for me*).. I'm trying custom dataset and it doesn't work :(. I've tried with rabbit but got error : "IndexError: too many indices for array: array is 2-dimensional, but 3 were indexed"

[Dumeowmeow]

No for the moment sadly (for me*).. I'm trying custom dataset and it doesn't work :(. I've tried with rabbit but got error : "IndexError: too many indices for array: array is 2-dimensional, but 3 were indexed"

Just modify line 149 in pred_poses.py: from original_masks = [np.array(Image.open(mask).resize(image.size))[:, :, 0] / 255.0 for mask, image in zip(masks, original_images)] to original_masks = [np.array(Image.open(mask).resize(image.size)) / 255.0 for mask, image in zip(masks, original_images)]

[TXSevenXT]

Thanks dude,

I've replied to another post few days ago (https://github.com/GaussianObject/GaussianObject/issues/52) but didn't reply in this one 😅

No for the moment sadly (for me*).. I'm trying custom dataset and it doesn't work :(. I've tried with rabbit but got error : "IndexError: too many indices for array: array is 2-dimensional, but 3 were indexed"

Just modify line 149 in pred_poses.py: from original_masks = [np.array(Image.open(mask).resize(image.size))[:, :, 0] / 255.0 for mask, image in zip(masks, original_images)] to original_masks = [np.array(Image.open(mask).resize(image.size)) / 255.0 for mask, image in zip(masks, original_images)]

[chensjtu]

Close this issue since it has been solved. Feel free to reopen~