RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation

  • 类型:arxiv
  • 标识:2606.22749
  • 链接:https://arxiv.org/abs/2606.22749
  • 主分类:multimodal
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:RaysUp is proposed, an ultra-lightweight, task-agnostic, and VFM-agnostic feature upsampling framework that reconstructs high-resolution feature maps at arbitrary resolutions that achieves state-of-the-art performance while using only 16% of the parameters of AnyUp and delivering approximately 7x faster inference.
  • OpenAlex ID:W7165685484
  • OpenAlex DOI:10.48550/arxiv.2606.22749
  • DOI:10.48550/arxiv.2606.22749
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2606.22749
  • OpenAlex更新:2026-07-19
  • 待LLM分类:否
  • 标题中文:RaysUp:基于几何感知光线表示的超轻量通用特征上采样
  • TLDR中文:本文提出 RaysUp,一个超轻量级、任务无关且与 VFM 无关的特征上采样框架,可在任意分辨率下重建高分辨率特征图,仅使用 AnyUp 16% 的参数即达到 SOTA 性能,推理速度提升约 7 倍。
  • 来源文件
  • /inbox/tom/_candidates/2026-06-30-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]