-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
-
Cosmetic Ingredient
- Water Treatment Chemical
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
Researchers from Gwangju Institute of Science and Technology in South Korea, the VinAI Institute in Vietnam, and the University of Waterloo in Canada have proposed a new way to improve the visual quality of path tracking using post-correction networks and self-supervised machine learning frameworks
Image source: Bochang Moon from Gwangju Institute of Science and Technology in South Korea
High-quality computer graphics, ubiquitous in games, illustrations, and visualizations, are considered to be the most advanced visual display technology
To address this, a team of researchers, including Jonghee Back and Associate Professor Bochang Moon of PhD students at the Gwangju Institute of Science and Technology in South Korea, Binh-Son Hua, a research scientist at the VinAI Institute in Vietnam, and Toshiya Hachisuka, an associate professor at the University of Waterloo in Canada, proposed a new MC denoising method in a new study that does not rely on references
"Not only do existing methods fail in very different test and training datasets, but it takes a long time to prepare the training datasets to pre-train the network
To achieve this, the team proposed a new denoising image post-correction method that includes a self-supervised machine learning framework and a post-correction network, essentially a convolutional neural network for image processing
To test the effectiveness of the proposed network, the team applied their method to the most advanced denoising methods available
"Our approach is the first one that doesn't rely on pre-training with external datasets
In fact, the technology could soon be applied to high-quality graphics rendering in video games, augmented reality, virtual reality, and metaverses!
