Material Editing Using a Physically Based Rendering Network
ICCV17 | 1936 | Material Editing Using a Physically Based Rendering Network
Guilin Liu (George Mason University), Duygu Ceylan (Adobe Research), Ersin Yumer (Adobe Research), Jimei Yang (University of California at Merced), Jyh-Ming Lien (George Mason University)
The ability to edit materials of objects in images is desirable by many content creators. However, this is an extremely challenging task as it requires to disentangle intrinsic physical properties of an image. We propose an end-to-end network architecture that replicates the forward image formation process to accomplish this task. Specifically, given a single image, the network first predicts intrinsic properties, i.e. shape, illumination, and material, which are then provided to a rendering layer. This layer performs in-network image synthesis, thereby enabling the network to understand the physics behind the image formation process. The proposed rendering layer is fully differentiable, supports both diffuse and specular materials, and thus can be applicable in a variety of problem settings. We demonstrate a rich set of visually plausible material editing examples and provide an extensive comparative study.
Nesta página do site você pode assistir ao vídeo on-line Material Editing Using a Physically Based Rendering Network duração hora minuto segundo em boa qualidade , que foi baixado pelo usuário ComputerVisionFoundation Videos 16 Novembro 2017, compartilhe o link com seus amigos e conhecidos, no youtube este vídeo já foi visto 269 vezes e gostou 1 espectadores. Boa visualização!
