用几何感知射线表示，实现高效通用的特征上采样。
RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation
- 将特征上采样转为几何感知射线域，利用6D射线坐标注入3D先验
- 参数量仅为AnyUp的16%，推理速度提升约7倍，性能达新基准
- 无需重训练，适配任意视觉模型与任务，适合部署场景
预训练视觉基础模型凭借强大的语义表征和泛化能力，已成为现代计算机视觉的核心。然而，其分块或池化输出本质上分辨率较低，限制了在需要细粒度像素级推理任务中的表现。现有特征上采样方法或损害语义保真度，或依赖特定模型重训练与复杂架构，影响效率与可扩展性。为此，我们提出RaysUp，一种超轻量、任务无关、模型无关的特征上采样框架，可在任意分辨率重建高分辨率特征图。不同于传统2D插值或注意力机制，RaysUp将特征重建引入几何感知射线域，提出空间解耦引导编码器以实现方向感知引导，任意分辨率交叉注意力机制支持分辨率灵活重构，并设计新颖的射线位置编码（RayPE），通过6D Plücker射线坐标注入隐式3D几何先验。最后，几何感知邻域注意力模块确保内容自适应双边聚合并保持几何一致性。跨多种密集预测任务的大量实验表明，RaysUp在仅使用AnyUp 16%参数量的同时，推理速度提升约7倍，性能达到新基准，显著改善精度-效率权衡，确立其作为通用特征上采样的实用且可扩展方案。代码已开源：https://github.com/MAP-RaysUp/RaysUp。
原文摘要 · Abstract (English)
Pre-trained Vision Foundation Models (VFMs) have become central to modern computer vision due to their powerful semantic representations and strong generalization ability. However, their patchified or pooled outputs are inherently low-resolution, limiting their effectiveness in tasks requiring fine-grained, pixel-level reasoning. Existing feature upsampling approaches either degrade semantic fidelity or rely on VFM-specific retraining and heavy architectures, hindering efficiency and scalability. To address these challenges, we propose RaysUp, an ultra-lightweight, task-agnostic, and VFM-agnostic feature upsampling framework that reconstructs high-resolution feature maps at arbitrary resolutions. Unlike conventional 2D interpolation or attention-based schemes, RaysUp lifts feature reconstruction into a geometry-aware ray domain. Specifically, we introduce a Spatially Decoupled Guidance Encoder for direction-aware guidance encoding, an Any-Resolution Cross-Attention mechanism for resolution-flexible reconstruction, and a novel Ray Positional Encoding (RayPE) that injects implicit 3D geometric priors via 6D Plucker ray coordinates. Finally, a Geometry-Aware Neighborhood Attention module further ensures content-adaptive bilateral aggregation while preserving geometric consistency. Extensive experiments across diverse dense prediction tasks demonstrate that RaysUp achieves state-of-the-art performance while using only 16% of the parameters of AnyUp and delivering approximately 7x faster inference. These results highlight a substantially improved accuracy-efficiency trade-off and establish RaysUp as a practical and scalable solution for universal feature upsampling. Code is available at https://github.com/MAP-RaysUp/RaysUp.
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。