📢 IntrinsiX: High-Quality PBR Generation using Image Priors 📢
Matthias Niessner
Открыть в X@MattNiessner50 тыс. подписчиков
21 957 просмотров
📢 IntrinsiX: High-Quality PBR Generation using Image Priors 📢
From text input, we generate renderable PBR maps! Next to editable image generation, our predictions can be distilled into room-scale scenes using SDS for large-scale PBR texture generation.
We first train separate LoRA modules for the intrinsic properties of albedo, rough/metal, normal. Then, we introduce cross-intrinsic attention using a rerendering loss with importance-weighted light sampling to enable coherent PBR generation.
Our method outperforms text -> image -> PBR methods both in generalization and quality, since directly generating PBR maps does not suffer from the inherent ambiguity of intrinsic image decomposition. In addition, our design choice facilitates SDS-based PBR texture distillation.
🌍
🎥
Great work by Peter Kocsis, Lukas Höllein
2 комментария
Комментарии из оригинального поста в X (Twitter)

@RedmondAI
Very cool, but not very useful in any production if you have to generate all output from a text prompt. Being able to drop in an image and have these layers extracted would be amazing.

@mattfigdore
This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.
15 531 отметка «Нравится»
