About the optimization stage between BANMo and Lab4D

[s0rrymaker77777]

Hi, thanks for your great work. I also tried BANMo before. I want to ask why lab4d takes so much less time than banmo and if lab4d contains three optimization stages in BANMo if I run lab4d 120 rounds. Thanks.

[gengshan-y]

Hi, lab4d runs a single-stage optimization as opposed to 3 stages in banmo.

The design goal of lab4d is to provide a simplified/unified codebase of BANMo, RAC, Total-Recon, PPR, etc, but keep the method the same.

I would say better engineering (or implementation details) plays a major role in terms of the speed-up. Here are some key differences:

	Lab4d	BANMo	Type of improvement
Sampling unit	Pixels	Lines/images	Fewer iterations
Camera Extrinsics	MLP + pre-training	Explicit+MLP	Fewer iterations
Camera Intrinsics	MLP + pre-training	Explicit	Fewer iterations
Rotation/Skinning Ops	(Dual) Quaternion	Matrix	Per eval time
Shape/Skinning MLP Size	Small	Large	Per eval time
Depth samples	64	128	Per eval time
2D-3D Features matching	Reuse sampled rays	New samples	Per eval time

[s0rrymaker77777]

Thanks for your explanation! By the way, have you already implemented the "comp" (fg+bg) situation in Lab4d?

[gengshan-y]

Yes, please check out this: https://lab4d-org.github.io/lab4d/tutorials/single_video_cat.html#reconstruct-the-total-scene

[s0rrymaker77777]

Thanks for your help!