AI Paper Atlas

Research map / 3D vision / 3D generation

Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description

Mahmoud Ahmed, Junjie Fei, Jian Ding, Eslam Mohamed Bakr, Mohamed Elhoseiny

ICCV 2025 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 13 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 query refinement levels (0 -> 2) in the segmentation decoder (ablation)Kestrel · 3DCoMPaT-GrIn PaPGDmIoU: 68.44 -> 86.70Improved
use Uni3D point encoder instead of PointBert (ablation)Kestrel · 3DCoMPaT-GrIn PaPGDmIoU: 77.05 -> 86.70 (with MLP projector)Improved
use MLP projector instead of Q-Former (ablation)Kestrel · 3DCoMPaT-GrIn PaPGDmIoU: 74.50 -> 86.70 (with Uni3D)Improved
add direct segmentation (DS) training data to grounded description data (ablation)Kestrel · 3DCoMPaT-GrIn Direct SegmentationmIoU: 49.97 -> 72.57Improved
add reasoning segmentation (RS) training data (ablation)Kestrel · 3DCoMPaT-GrIn Reasoning SegmentationmIoU: 52.03 -> 71.8Improved
increase direct segmentation data from 8K to 40K samples (ablation)Kestrel · 3DCoMPaT-GrIn Grounded DescriptionmIoU: GD mIoU 86.07 -> 81.37; DS mIoU 78.78 -> 79.86Mixed
use Kestrel instead of SegPoint reimplementation3D MLLM segmentation grounding · 3DCoMPaT-GrIn Reasoning SegmentationmIoU: 65.20 -> 71.80Improved
use 3D point input instead of 2D-view uplifting (Kestrel vs PARIS3D)part grounding · 3DCoMPaT-GrIn Direct SegmentationmIoU: 37.99 -> 78.78Improved
Kestrel zero-shot vs PartSTAD on PartNet-MobilityKestrel · PartNet-Mobilityoverall accuracy: 65.0 vs 47.7 zero-shot, 63.9 few-shotHurt

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