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 up-sampling 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. An important limitation of such pre-trained models, which are usually transformer-based, is that their output feature map resolution is limited to the number of transformer tokens, preventing the prediction of pixel-level features. Therefore, several recent works, such as FeatUp (Fu et al., 2024), LoftUp (Huang et al., 2025), or JAFAR (Couairon et al., 2025) propose learned feature upsampling methods. While such feature upsampling methods perform well when paired with the vision encoders with which they were trained, they are generally not encoder-agnostic at inference time and need to be retrained to be usable with a different feature extractor. This can be costly or, in the case of the latest large vision models (Sim eoni et al., 2025), even infeasible with limited computing resources, 1 AnyUp is the first learnable method that generalizes to any input feature at inference time, while being able to upsample from any to any resolution and being task-agnostic.

High-res features can be learned either as a per-image implicit network or a general-purpose upsampling operation; the latter is a drop-in module to improve downstream dense prediction tasks. Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero-or few-shot regime. However, these features often lack the spatial resolution to directly perform dense prediction tasks like segmentation and depth prediction because models aggressively pool information over large areas. In this work, we introduce FeatUp, a task-and model-agnostic framework to restore lost spatial information in deep features. We introduce two variants of FeatUp: one that guides features with high-resolution signal in a single forward pass, and one that fits an implicit model to a single image to reconstruct features at any resolution. Both approaches use a multi-view consistency loss with deep analogies to NeRFs. Our features retain their original semantics and can be swapped into existing applications to yield resolution and performance gains even without re-training. We show that FeatUp significantly outperforms other feature upsampling and image super-resolution approaches in class activation map generation, transfer learning for segmentation and depth prediction, and end-to-end training for semantic segmentation. Despite their immense success, deep features often sacrifice spatial resolution for semantic quality. For example, ResNet-50 (He et al., 2015) produces 7 7 deep Work done while at MIT. FeatUp learns to upsample features through a consistency loss on low resolution "views" of a model's features that arise from slight transformations of the input image. Even Vision Transformers (ViTs) (Dosovitskiy et al., 2020) incur a significant resolution reduction, making it challenging to perform dense prediction tasks such as segmentation or depth estimation using these features alone. To mitigate these issues, we propose FeatUp: a novel framework to improve the resolution of any vision model's features without changing their original "meaning" or orientation. Our primary insight, inspired by 3D reconstruction frameworks like NeRF (Mildenhall et al., 2020), is that multiview consistency of low-resolution signals can supervise the construction of high-resolution signals. More specifically, we learn high-resolution information by aggregating low resolution views from a model's outputs across multiple "jittered" (e.g. Our work explores two architectures for upsampling: a single guided upsampling feedforward network that generalizes across images, and an implicit representation overfit to a single image.