无需训练即可将低分辨率特征恢复为高分辨率，通用且快速。
Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling
- 通过每张图优化学习非各向同性高斯核，融合空间与范围信息。
- 在224x224图像上仅需0.419秒，实现分割/深度/概率图的最优重建。
- 适用于多种模型与模态，无需重训练，适合部署在边缘设备。
我们提出 extbf{Upsample Anything}，一种轻量级测试时优化（TTO）框架，可在无任何训练的情况下将低分辨率特征恢复为像素级高分辨率输出。尽管视觉基础模型在多样化下游任务中表现强大，但其表征通常被下采样14倍/16倍（如ViT），限制了其在像素级应用中的直接使用。现有特征上采样方法依赖于数据集特定的再训练或复杂的隐式优化，制约了可扩展性与泛化能力。Upsample Anything 通过简单的逐图像优化，学习一个结合空间与范围线索的非各向同性高斯核，有效融合高斯泼溅与联合双边上采样。该学习核作为通用、边缘感知算子，可无缝跨架构与模态迁移，实现特征、深度或概率图的精确高分辨率重建。其运行速度约为每张224x224图像0.419秒，在语义分割、深度估计及深度与概率图上采样任务中达到当前最优性能。
原文摘要 · Abstract (English)
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/}
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。