search

tum-vision / fusenet

This repository is the official release of the code for the following paper "FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-based CNN Architecture" which is published at the 13th Asian Conference on Computer Vision (ACCV 2016).
Other
127 stars 40 forks source link

Depth normalization #13

Closed KengChiLiu closed 6 years ago

KengChiLiu commented 6 years ago

Hi @tum-vision @hazirbas In paper, it says the you normalize depth map to [0,255] Does it mean to map 16bits [0,65535] to [0,255] or to map [min,max] of the depth map to [0,255] ? By the way, did you normalize too when only training with depth ?

Thank you

KengChiLiu commented 6 years ago

@hazirbas

hazirbas commented 6 years ago

Hey, min,max to 0,255. But do the normalization on the depth values, D/1000.0, It might not look important however will definitely affect the scale.