AI Paper Atlas

Research map / 3D vision / 3D generation

ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail

Chandan Yeshwanth, Dávid Rozenberszki, Angela Dai

ICCV 2025 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 5 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 semantic consistency loss (ablation)separate-captioner baseline · part-level captionsCIDEr@0.5: 18.7 -> 24.8Improved
add semantic consistency loss (ablation)separate-captioner baseline · object-level captionsCIDEr@0.5: 29.8 -> 30.2Improved
add textual consistency loss (ablation)separate-captioner baseline · object-level captionsCIDEr@0.5: 29.8 -> 32.2Improved
add textual consistency loss (ablation)separate-captioner baseline · part-level captionsCIDEr@0.5: 18.7 -> 19.6Improved
add part-to-object information sharing (ablation)separate-captioner baseline · object-level captionsCIDEr@0.5: 29.8 -> 34.8Improved
add part-to-object information sharing (ablation)separate-captioner baseline · part-level captionsCIDEr@0.5: 18.7 -> 25.4Improved
combine consistency losses with information sharing (full model) (ablation)part-to-object sharing only · part-level captionsCIDEr@0.5: 25.4 -> 32.3Improved
combine consistency losses with information sharing (full model) (ablation)part-to-object sharing only · object-level captionsCIDEr@0.5: 34.8 -> 32.7Hurt
use part-to-object instead of object-to-part information sharing (ablation)ExCap3D · part-level captionsCIDEr@0.5: 15.6 -> 32.3Improved
use part-to-object instead of object-to-part information sharing (ablation)ExCap3D · object-level captionsCIDEr@0.5: 32.8 -> 32.7No clear effect
add segment-level context features (ablation)ExCap3D · part-level captionsCIDEr@0.5: 27.0 -> 32.3Improved
add segment-level context features (ablation)ExCap3D · object-level captionsCIDEr@0.5: 33.7 -> 32.7Hurt

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