AI Paper Atlas

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

Multi-scenario Overlapping Text Segmentation with Depth Awareness

Yang Liu, Xudong Xie, Yuliang Liu, Xiang Bai

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 2 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 HSOT synthetic pre-training (ablation)Mask2Former · MOT testIoU Ov: 52.82 -> 59.56Improved
add HSOT synthetic pre-training (ablation)Mask2Former · MOT testmIoU Text: 70.28 -> 74.18Improved
add depth-guided decoder (ablation)Mask2Former + HSOT · MOT testmIoU Text: 74.18 -> 75.53Improved
add depth-guided decoder (ablation)Mask2Former + HSOT · MOT testIoU Occd: 76.98 -> 79.17Improved
add depth-guided decoder without pre-training (ablation)Mask2Former · MOT testmIoU Text: 70.28 -> 72.55Improved
increase synthetic pre-training data from 140k to 280k (ablation)Ours pre-train · MOT testmIoU Text: 74.86 -> 75.53Improved
increase synthetic pre-training data from 280k to 350k (ablation)Ours pre-train · MOT testmIoU Text: 75.53 -> 75.59No clear effect
add scene-related synthetic data only (ablation)Ours (real data only) · MOT testmIoU Text: 72.55 -> 73.24Improved
add document-related synthetic data only (ablation)Ours (real data only) · MOT testmIoU Text: 72.55 -> 75.13Improved
combine document and scene synthetic data (ablation)pre-training on one data type · MOT testmIoU Text: 75.13 -> 75.53Improved
segment overlapping text before recognition (ablation)SVTRv2 recognizer · MOT test subsetrecognition accuracy: 4.04 -> 78.15Improved
use depth-guided model vs MFMMFM · SignaTR6KPT IoU: 73.05 -> 90.46Improved

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