ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2306.00987
23
34

StyleGAN knows Normal, Depth, Albedo, and More

1 June 2023
Anand Bhattad
Daniel McKee
Derek Hoiem
David A. Forsyth
    GAN
ArXivPDFHTML
Abstract

Intrinsic images, in the original sense, are image-like maps of scene properties like depth, normal, albedo or shading. This paper demonstrates that StyleGAN can easily be induced to produce intrinsic images. The procedure is straightforward. We show that, if StyleGAN produces G(w)G({w})G(w) from latents w{w}w, then for each type of intrinsic image, there is a fixed offset dc{d}_cdc​ so that G(w+dc)G({w}+{d}_c)G(w+dc​) is that type of intrinsic image for G(w)G({w})G(w). Here dc{d}_cdc​ is {\em independent of w{w}w}. The StyleGAN we used was pretrained by others, so this property is not some accident of our training regime. We show that there are image transformations StyleGAN will {\em not} produce in this fashion, so StyleGAN is not a generic image regression engine. It is conceptually exciting that an image generator should ``know'' and represent intrinsic images. There may also be practical advantages to using a generative model to produce intrinsic images. The intrinsic images obtained from StyleGAN compare well both qualitatively and quantitatively with those obtained by using SOTA image regression techniques; but StyleGAN's intrinsic images are robust to relighting effects, unlike SOTA methods.

View on arXiv
Comments on this paper