The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
ATD: Improved Transformer With Adaptive Token Dictionary for Image Restoration
- Published
- Record updated
Summary
The paper proposes ATD, a transformer architecture for image restoration that models global dependencies with linear complexity relative to image size. It uses a learnable token dictionary and token dictionary cross-attention (TDCA) to group features into categories, and reports state-of-the-art results on multiple image super-resolution benchmarks, plus ATD-U for denoising and JPEG artifact removal.