Kavli Affiliate: Michael Wimmer
| First 5 Authors: Thomas Wimmer, Thomas Wimmer, , ,

| Summary:
We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an inference-time feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiments, AnyUp sets a new state of the art for upsampled features, generalizes to different feature types, and preserves feature semantics while being efficient and easy to apply to a wide range of downstream tasks.
| Search Query: arXiv Query: search_query=au:”Wimmer Michael”&id_list=&start=0&max_results=3
Read More