According to DSO paper for Step 2: Keyframe Creation we need to calculate simply and straightforwardly 2 mean square optical flows f and f_t.
As I understand, they are calculated in CoarseTracker.cpp - here and these calculations are strange and discouraging for me - I can't understand why we need additional residual with negative (according to code comments) transformation ((R, -T) for f and (I, -T) for f_t) for every usual residual with positive transformation ((R, T) for f and (I, T) for f_t).
I can't understand why only 1 positive transformation isn't enough, why we need so special additional negative transformation with negative translation only and what it gives to us - why it is better.
Hello!
According to DSO paper for
Step 2: Keyframe Creationwe need to calculate simply and straightforwardly 2 mean square optical flowsfandf_t.As I understand, they are calculated in CoarseTracker.cpp - here and these calculations are strange and discouraging for me - I can't understand why we need additional residual with
negative(according to code comments) transformation ((R, -T)forfand(I, -T)forf_t) for every usual residual withpositivetransformation ((R, T)forfand(I, T)forf_t).I can't understand why only 1
positivetransformation isn't enough, why we need so special additionalnegativetransformation with negative translation only and what it gives to us - why it is better.Can anyone help me please? Thanks in advance!