Published • loading... • Updated
AMD’s "PEPS" Research Pushes Neural Texture Compression Further, Cutting Model Parameters By 25% At Comparable Quality
Summary by Wccftech
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.2 Articles
2 Articles
AMD has introduced PEPS ("Positional Encoding Projected Sampling") as a method for neuronal texture compression, which requires around 25 percent fewer parameters with comparable quality. On Radeon GPUs, it does not matter yet.
AMD’s "PEPS" Research Pushes Neural Texture Compression Further, Cutting Model Parameters By 25% At Comparable Quality
AMD presented new research at the I3D Symposium titled "PEPS: Positional Encoding Projected Sampling", introducing a new method for positional encoding that can improve neural texture compression. How Does Neural Texture Compression Work? Neural Texture Compression works by training what are known as INRs, or “Implicit Neural Representations,” to learn coordinate-to-signal functions. By projecting texture coordinates into a higher-dimensional em…
Coverage Details
Total News Sources2
Leaning Left0Leaning Right0Center0Last UpdatedBias DistributionNo sources with tracked biases.
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
