Some bad results in NeRF Synthetic dataset
ZyyZyy06 opened this issue · 4 comments
ZyyZyy06 commented
hbb1 commented
How did you train the scenes? Do you mean the optimized results are random?
ZyyZyy06 commented
hbb1 commented
We haven't thoroughly tested the regularization for nerf synthetic dataset yet. One solution is to use the render_alpha for masking the normal loss in the background regions.
ZyyZyy06 commented
Ok, thanks for the answer, it's just a small flaw in the background area on the synthetic dataset that makes me feel confused