Search Results for author:
Found 3 papers, 0 papers with code
Token Recycling for Efficient Sequential Inference with Vision Transformers
To reduce this computational inefficiency, we introduce the TOken REcycling (TORE) modification for the ViT inference, which can be used with any architecture.
Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers
Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches.
HashCC: Lightweight Method to Improve the Quality of the Camera-less NeRF Scene Generation
Neural Radiance Fields has become a prominent method of scene generation via view synthesis.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
