# Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling

Source: [Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling](<https://www.sota2.com/research/paper/691ff1f1d6b0dd334292e568>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-28T06:00:01.666Z

Authors: Minseok Seo, Mark Hamilton, Changick Kim

Published: 2025-11-20T12:27:53.000Z

## Abstract

We present \\textbf{Upsample Anything}, a lightweight test-time optimization (TTO) framework that restores low-resolution features to high-resolution, pixel-wise outputs without any training. Although Vision Foundation Models demonstrate strong generalization across diverse downstream tasks, their representations are typically downsampled by 14x/16x (e.g., ViT), which limits their direct use in pixel-level applications. Existing feature upsampling approaches depend on dataset-specific retraining or heavy implicit optimization, restricting scalability and generalization. Upsample Anything addresses these issues through a simple per-image optimization that learns an anisotropic Gaussian kernel combining spatial and range cues, effectively bridging Gaussian Splatting and Joint Bilateral Upsampling. The learned kernel acts as a universal, edge-aware operator that transfers seamlessly across architectures and modalities, enabling precise high-resolution reconstruction of features, depth, or probability maps. It runs in only $\\approx0.419 \\text{s}$ per 224x224 image and achieves state-of-the-art performance on semantic segmentation, depth estimation, and both depth and probability map upsampling. \\textbf{Project page:} \\href{https://seominseok0429.github.io/Upsample-Anything/}{https://seominseok0429.github.io/Upsample-Anything/}

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.16301>)

[PDF](<https://arxiv.org/pdf/2511.16301.pdf>)

[Implementation](<https://github.com/seominseok0429/Upsample-Anything-A-Simple-and-Hard-to-Beat-Baseline-for-Feature-Upsampling>)
