Thanks for sharing the amazing work. We are trying to compare with UHM for personalization.
However, we want to see if this codebase is sufficient for the comparison in our setting. In particular, given one or more RGB images of a right hand, we would like to use UHM to learn a personalized hand avatar. After this avatar is learnt, given an environment map in HDRI (e.g., in exr) format, and a set of MANO poses, can this codebase yield the relit hand images?
Hi Alex, you can use phone reflectance model (or any other PBR-based relighting) to relight UHM as it is fully mesh-based one. UHM is not compatible with MANO poses.
Hi Gyeongsik,
Nice to meet you in ECCV HANDS workshop. :)
Thanks for sharing the amazing work. We are trying to compare with UHM for personalization.
However, we want to see if this codebase is sufficient for the comparison in our setting. In particular, given one or more RGB images of a right hand, we would like to use UHM to learn a personalized hand avatar. After this avatar is learnt, given an environment map in HDRI (e.g., in exr) format, and a set of MANO poses, can this codebase yield the relit hand images?
Thanks!