Joint training depth and flow about geonet HOT 4 CLOSED

Hi @SeokjuLee , actually I experimented with finetuning all the networks together but found no improvement. This is explained in the Training Details in the experimental part of our paper:

Though the sub-networks can be trained together in an end-to-end fashion, there is no guarantee that the local gradient optimization could get the network to that optimal point. Therefore, we adopt a stage-wise training strategy

from geonet.

@yzcjtr Thanks for the reply. So the ResFlowNet doesn't affect the performance of depth estimation. Is this right? Table 1 shows GeoNet performs significantly better than SfM-Learner [56]. Do SSIM loss and network structure (vgg, resnet) make this huge performance gap?

from geonet.

Yes. Both loss and architecture account for the improvement. You can see detailed analysis in Sec 4.2 of our paper.

from geonet.

@yzcjtr Thank you!

from geonet.