It improves the original ESRGAN neural network and uses a dual-stream network to process low-resolution original images and high-resolution channel information graphs respectively. To further improve the reconstruction result, we used a new algorithm. Then we bring in reflection, transparency, metal, and roughness info to optimize reflection and highlight effects. Technically, the D5 R & D team has done the following:įirst, we use high-resolution albedo and normal information to reconstruct texture and geometric features. Therefore, we introduced these 3D information as input features to produce a better result. However, at first we did not have enough information of 3D scenes such as geometry, materials, and textures, leading to a gap between the reconstruction and the physical rendering results. The neural network can effectively make use of the prior information learned from this training data to give us a better high-resolution reconstruction.
That's because D5 SR added the geometry, material, texture and other info of this object to improve the quality of reconstructed high-res images.ĭ5 team trains the SR algorithm with a vast collection of images generated by D5. Yet, this problem is well tackled with D5 SR, as you can see in the following test images. Therefore, when doubling the resolution of rendered images, real-esrgan may have some obvious artifacts such as unnatural materials. Real-esrgan is a blind super-resolution algorithm that has not been specifically trained for D5 Render images. Highlights of D5 SR More Realistic Reconstruction For instance, it can enhance the details and resolution in video rendering, and in real-time rendering, it can increase the frame rate to improve user experience.īut let's be honest, amplifying the resolution of rendered images without distortion has always been a tough nut to crack. The Super Resolution tech can be used in a wide range of applications. "SR" stands for "Super Resolution", a D5's self-developed tech that transforms low-res images into high-res ones.īased on neural network super-resolution image generation algorithm, D5 SR is combined with multi-channel rendering feature maps to significantly speed up image rendering. D5 Render has rolled out a new feature "D5 SR Image Rendering" in the latest version 2.5.
0 kommentar(er)
