AI Paper Atlas

Research map / 3D vision / 3D generation

NegROI: Click-Centric Uncertainty-Guided Refinement with Scene-Conditioned Negative Prompts for Robust Interactive 3D Segmentation

shuheng zhang, Feng Wu

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
add scene-conditioned negative prompts (ablation)NegROI base · ScanNet40IoU@1: 67.0 -> 69.2Improved
add scene-conditioned negative prompts (ablation)NegROI base · S3DISIoU@1: 62.5 -> 64.2Improved
add click-centric fine-grid ROI refinement (ablation)NegROI + NEG prompts · ScanNet40IoU@1: 69.2 -> 70.9Improved
add click-centric fine-grid ROI refinement (ablation)NegROI + NEG prompts · S3DISIoU@1: 64.2 -> 65.8Improved
add uncertainty-driven ROI selection (ablation)NegROI + ROI · ScanNet40IoU@1: 70.9 -> 71.8Improved
add uncertainty-driven ROI selection (ablation)NegROI + ROI · ScanNet40IoU@10: 83.0 -> 82.8Hurt
add boundary hard negative loss L_hn (ablation)NegROI + uncertainty ROI · ScanNet40IoU@1: 71.8 -> 71.2Hurt
add boundary hard negative loss L_hn (ablation)NegROI + uncertainty ROI · S3DISIoU@10: 87.4 -> 87.1Hurt
add diversity regularizer L_div (ablation)NegROI + L_hn · ScanNet40IoU@1: 71.2 -> 72.1Improved
add diversity regularizer L_div (ablation)NegROI + L_hn · S3DISIoU@1: 65.6 -> 66.9Improved
add full NegROI (all components) over base (ablation)NegROI · ScanNet40IoU@10: 80.8 -> 83.6Improved
use NegROI instead of Easy3D, out-of-domain to KITTI-360NegROI · KITTI-360 (train ScanNet40)IoU@10: 83.6 -> 87.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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