Information
- Replaced by: zsolnaifeher-2020-pme
- Publication Type: Technical Report
- Workgroup(s)/Project(s):
- Date: September 2019
- Number: TR-193-02-2019-3
- Open Access: yes
- Keywords: neural rendering, neural networks, photorealistic rendering, photorealistic material editing
Abstract
Creating photorealistic materials for light transport algorithms requires carefully fine-tuning a set of material properties to achieve a desired artistic effect. This is typically a lengthy process that involves a trained artist with specialized knowledge. In this work, we present a technique that aims to empower novice and intermediate-level users to synthesize high-quality photorealistic materials by only requiring basic image processing knowledge. In the proposed workflow, the user starts with an input image and applies a few intuitive transforms (e.g., colorization, image inpainting) within a 2D image editor of their choice, and in the next step, our technique produces a photorealistic result that approximates this target image. Our method combines the advantages of a neural network-augmented optimizer and an encoder neural network to produce high-quality output results within 30 seconds. We also demonstrate that it is resilient against poorly-edited target images and propose a simple extension to predict image sequences with a strict time budget of 1-2 seconds per image.Video: https://www.youtube.com/watch?v=8eNHEaxsj18
Additional Files and Images
Additional images and videos
Additional files
Weblinks
BibTeX
@techreport{zsolnaifeher-2019-pme, title = "Photorealistic Material Editing Through Direct Image Manipulation", author = "Karoly Zsolnai-Feh\'{e}r and Peter Wonka and Michael Wimmer", year = "2019", abstract = "Creating photorealistic materials for light transport algorithms requires carefully fine-tuning a set of material properties to achieve a desired artistic effect. This is typically a lengthy process that involves a trained artist with specialized knowledge. In this work, we present a technique that aims to empower novice and intermediate-level users to synthesize high-quality photorealistic materials by only requiring basic image processing knowledge. In the proposed workflow, the user starts with an input image and applies a few intuitive transforms (e.g., colorization, image inpainting) within a 2D image editor of their choice, and in the next step, our technique produces a photorealistic result that approximates this target image. Our method combines the advantages of a neural network-augmented optimizer and an encoder neural network to produce high-quality output results within 30 seconds. We also demonstrate that it is resilient against poorly-edited target images and propose a simple extension to predict image sequences with a strict time budget of 1-2 seconds per image. Video: https://www.youtube.com/watch?v=8eNHEaxsj18", month = sep, number = "TR-193-02-2019-3", address = "Favoritenstrasse 9-11/E193-02, A-1040 Vienna, Austria", institution = "Research Unit of Computer Graphics, Institute of Visual Computing and Human-Centered Technology, Faculty of Informatics, TU Wien ", note = "human contact: technical-report@cg.tuwien.ac.at", keywords = "neural rendering, neural networks, photorealistic rendering, photorealistic material editing", URL = "https://www.cg.tuwien.ac.at/research/publications/2019/zsolnaifeher-2019-pme/", }