George Kopanas
@grgkopanas.bsky.social
Research Scientist @Google + Climbing Gym Owner. Previously PhD at @Inria | Intern at @Adobe | SWE at @Arm
You are right! But feels like it's a much harder problem to find hyper realistic materials and geometry at scale than actually rendering them with PB algorithms.
December 15, 2024 at 7:32 PM
You are right! But feels like it's a much harder problem to find hyper realistic materials and geometry at scale than actually rendering them with PB algorithms.
True, but one can argue that if you don't scan real materials and real geometry you are losing some signal too. There needs to be a balance between the domain gap and the readiness/cost of data. Imo the problem is more that we don't have assets and less about how we render them.
December 15, 2024 at 5:12 PM
True, but one can argue that if you don't scan real materials and real geometry you are losing some signal too. There needs to be a balance between the domain gap and the readiness/cost of data. Imo the problem is more that we don't have assets and less about how we render them.