InfiniTAM
InfiniTAM copied to clipboard
Number of modified gradients is slightly different for GPU & CPU for data + LS term warp gradient computation
Confirm that exact comparison failure for line 193 (currently, commented) of Test_WarpGradient_CUDA_VBH is caused by numerical discrepancies between CPU & CUDA, nothing more.
Needs re-testing again (LS term was changed recently).