AI Paper Atlas

Research map / 3D vision / Face and shape

RI-Mamba: Rotation-Invariant Mamba for Robust Text-to-Shape Retrieval

Khanh Nguyen, Dasith de Silva Edirimuni, Ghulam Mubashar Hassan, Ajmal Mian

CVPR 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching · 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 Hilbert sorting (ablation)RI-Mamba · Omni3D (ShapeNet pretraining)accuracy: 13.9 -> 14.7Improved
add reference frame disambiguation (RFD) (ablation)RI-Mamba · Omni3D (ShapeNet pretraining)accuracy: 14.1 -> 14.7Improved
add positional and orientational embeddings with FiLM (ablation)RI-Mamba · Omni3D (ShapeNet pretraining)accuracy: 8.2 -> 14.7Improved
add adaptive FiLM to pos and ori embeddings (ablation)RI-Mamba · Omni3D (ShapeNet pretraining)accuracy: 13.1 -> 14.7Improved
add bidirectional scanning (ablation)RI-Mamba · Omni3D (ShapeNet pretraining)accuracy: 12.7 -> 14.7Improved
use RI-Mamba instead of SCA3D under random rotationRI-Mamba · Text2Shape-SO(3)RR@1: 2.24 -> 13.20Improved
use RI-Mamba instead of SCA3D (which uses part labels) on canonical posesRI-Mamba · Text2ShapeRR@5: 35.11 -> 34.57No clear effect
apply random rotation to database for non-RI DuoMambaDuoMamba · OmniObject3D text-to-3D (Ensemble)RR@1: 15.82 -> 7.83Hurt
scale pretraining data from ShapeNet to EnsembleRI-Mamba · OmniObject3D text-to-3DRR@1: 8.39 -> 19.02Improved
use RI-Mamba instead of RI-TransformerRI-Mamba · OmniObject3D-SO(3) text-to-3D (Ensemble)RR@1: 10.39 -> 19.34Improved
use RI-Mamba instead of RI-Transformer on ModelNet40 classificationRI-Mamba · ModelNet40 (Ensemble)accuracy: 78.3 -> 76.7Hurt
use RI-Mamba instead of PointBERT-TAMM on canonical 3D-to-3D retrievalRI-Mamba · OmniObject3D 3D-to-3D I/I (Ensemble)mAP: 49.84 -> 47.58Hurt

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