Madaoer

@Xiaxia1997 May I ask you how do you get psnr results with pose refinement using nerfstudio? Because I find that the images generated by nerfstudio don't align with ground truth

@vincepapaix well, maybe I solve this problem. If you turn camera optimizer off, it should be aligned between output and ground truth, if you turn it on, we should use...

> @tancik With the last changes still got None, this time during training on the Lego scene with the default number of steps with a disabled collider, camera optimizer, and...

In my case, this error can be sovled by turn off the camera pose optimize, but the image generated by nerfacto will be very bad. I have made the change...

@snarb Thank you snarb. In my setting, adding torch.sigmoid in field function does make training process more stable. However, it seems to harm the image quality in eval set, tending...

Sorry for the late reply. I think you can try a smaller s3im loss weight.

Sorry for the late reply. I think these files are from Replica dataset. You can donwload [Replica](https://s3.eu-central-1.amazonaws.com/avg-projects/monosdf/data/Replica.tar) dataset here.

Hi, I think you can modify [code](https://github.com/Madaoer/S3IM-Neural-Fields/blob/dfa2365e623133e00ae2f0e75c0cc4d78b737a84/model_components/s3im.py#L39) to adapt it for single-channel processing.