AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Neuroverse3D: Developing In-Context Learning Universal Model for Neuroimaging in 3D

Jiesi Hu, Hanyang Peng, Yanwu Yang, Xutao Guo, Yang Shang, Pengcheng Shi, Chenfei Ye, Ting Ma

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 0 citations (OpenAlex)

Read the paper

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 modified cubic smooth-L1 segmentation loss (ablation)Neuroverse3D · Held-out segmentation avgDice: 0.7977 -> 0.8173Improved
add gradient (intensity difference) loss (ablation)Neuroverse3D · Held-out generation avgPSNR: 26.67 -> 28.38Improved
add gradient loss (not applied to segmentation tasks) (ablation)Neuroverse3D · Held-out segmentation avgDice: 0.8014 -> 0.8173Improved
add modified smooth-L1 loss (ablation)Neuroverse3D · Held-out generation avgPSNR: 28.19 -> 28.38No clear effect
increase context size (ablation)Neuroverse3D · Held-out tasksDice / PSNRImproved
extend fusion from deepest stage only to stages 5-1 (ablation)Neuroverse3D · PET segmentation (unseen modality)Dice: 0.2870 -> 0.5314Improved
extend fusion from deepest stage only to stages 5-1 (ablation)Neuroverse3D · Held-out generationPSNR: 25.82 -> 28.87Improved
use context image modality mismatched with target (ablation)Neuroverse3D · 2D-to-3D, T1 targetPSNR: 26.63 -> 12.27 (CT context)Hurt
train without target task (Neuroverse3D-unseen) for segmentation (ablation)Neuroverse3D · Held-out unseen segmentation tasksDice: about 5-point decreaseHurt
use 3D ICL model instead of 2D slice-wise ICL modelsICL models · Hippocampus, thalamus, lateral ventricle, putamenDice: over 20 Dice pointsImproved
use 3D context model instead of 2D models for modality transform and super-resolutionNeuroverse3D · generation tasksPSNRNo clear effect
use APSP with different mini-context sizes (ablation)Neuroverse3D · inference on V100memory / output: 7.35GB at l=1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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