AI Paper Atlas

Research map / 3D vision / 3D generation

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

Ding Yuchuan, Linfei Li, Lin Zhang, Ying Shen

ECCV 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace image-grid RoPE/no PE with RayPE (ablation)RaysUp · avg mIoU over 4 VFMsmIoU: 81.05 -> 82.17 (None -> RayPE); RoPE 81.92Improved
use RayPE instead of RoPE (ablation)RaysUp · avg mIoU over 4 VFMsmIoU: 81.92 -> 82.17Improved
use RayPE instead of SinRays (ablation)RaysUp · avg mIoU over 4 VFMsmIoU: 81.59 -> 82.17Improved
use decoupled-branch guidance encoder instead of single-branch (ablation)RaysUp · avg mIoU over 4 VFMsmIoU / params: 81.87 -> 82.17; 0.266M -> 0.14MImproved
increase guidance dim from 256 to 512 or 768 (ablation)RaysUp · avg mIoU over 4 VFMsmIoU: 82.17 -> 82.20 (512), 82.19 (768); params 0.14M -> 0.40M/0.89MNo clear effect
reduce guidance dim from 256 to 128 (ablation)RaysUp · avg mIoU over 4 VFMsmIoU: 82.17 -> 82.02Hurt
increase guidance conv blocks from L=1 to L=3 (ablation)RaysUp · avg mIoU over 4 VFMsmIoU: 82.17 -> 82.44; params 0.14M -> 0.27MImproved
use DA3 predicted pose instead of identity pose (ablation)RaysUp · avg mIoU over 4 VFMsmIoU: 82.17 -> 82.41 (DA3-Small), 82.44 (DA3-Base)Improved
add local-crop training strategy (ablation)RaysUp · Cityscapes segmentationmIoU: 61.88 -> 63.04Improved
RaysUp vs LoftUp on open-vocabulary segmentationRaysUp · COCO-Stuff / Pascal-VOC / ADE20K / Cityscapes open-vocabmIoU: COCO-Stuff 27.54 (LoftUp) vs 27.11Hurt
RaysUp vs AnyUp across backbonesRaysUp · Pascal-VOC segmentation across DINOv2/DINOv3/SigLIP2/PE SpatialmIoU: e.g. DINOv3 ViT-S 81.97 -> 82.60; SigLIP2 ViT-B 78.70 -> 79.37Improved
RaysUp vs AnyUp efficiencyRaysUp · 224x224 upsamplingFPS / params: 11 -> 55 FPS; 0.87M -> 0.14M paramsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy