AI Paper Atlas

Research map / 3D vision / 3D generation

Rosetum3D: A Large-Scale 3D Vision Dataset from Preharvest Roses

Songyan Liu, Xipei Liu, Yujie Liu, Jiali Wu, Xiaofei Liu

ECCV 2026 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 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
fine-tune depth models on Rosetum3D instead of zero-shot NYU-trained (ablation)monocular depth models · Rosetum3D monocular depthAbsRel: 0.498 -> 0.165 (best zero-shot Depth Anything vs best fine-tuned BinsFormer)Improved
use ground-truth boxes instead of YOLOv5 detections for top-down keypoints (ablation)ViTPose · Rosetum3D 2D keypoint localizationAP: 21.9 -> 42.1Improved
top-down vs bottom-up keypoint methods with detected boxesViTPose vs DEKR+HRNet · Rosetum3D 2D keypoint localizationAP: 24.9 -> 21.9 (top-down)Hurt
add multi-frame temporal optimization to 3D localization (ablation)ViTPose + DETR · Rosetum3D 3D rose localizationMPJPE (mm): 556.8 -> 539.1Improved
add multi-frame temporal optimization to 3D localization (ablation)RTMPose + DETR · Rosetum3D 3D rose localizationMPJPE (mm): 558.4 -> 542.2Improved
use predicted depth instead of ground-truth depth for 3D keypointsViTPose + DETR · Rosetum3D 3D rose localizationMPJPE (mm): 556.8 -> 647.2 (BinsFormer depth)Hurt
replace Depth Anything with fine-tuned BinsFormer for depth (ablation)ViTPose + DETR · Rosetum3D 3D rose localizationMPJPE (mm): 656.9 -> 647.2Improved
compare detectors YOLOv5 vs DETR familyobject detectors · Rosetum3D 2D detectionAP: 35.0 (YOLOv5) vs 33.0 (DETR) AP; AP50 67.1 vs 66.5Mixed

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