# SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification

arXiv: https://arxiv.org/abs/2506.21056 · HTML: https://mlsanity.com/paper/2506.21056/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding](https://mlsanity.com/paper/2311.18482/) (2023)
- [EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI](https://mlsanity.com/paper/2312.16170/) (2023)
- [HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting](https://mlsanity.com/paper/2403.12722/) (2024)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation](https://mlsanity.com/paper/2306.10013/) (2023)
- [RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding](https://mlsanity.com/paper/2304.00962/) (2023)
- [RevealNet: Seeing Behind Objects in RGB-D Scans](https://mlsanity.com/paper/1904.12012/) (2019)
- [Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training](https://mlsanity.com/paper/2311.01734/) (2023)
- [PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation](https://mlsanity.com/paper/2409.06535/) (2024)
- [Multi-modal Relation Distillation for Unified 3D Representation Learning](https://mlsanity.com/paper/2407.14007/) (2024)
- [Object Instance Retrieval in Assistive Robotics: Leveraging Fine-Tuned SimSiam with Multi-View Images Based on 3D Semantic Map](https://mlsanity.com/paper/2404.09647/) (2024)
- [TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval](https://mlsanity.com/paper/2304.06053/) (2023)
- [SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval](https://mlsanity.com/paper/2304.05731/) (2023)

## Abstract (arXiv)

Retrieving 3D objects in complex indoor environments using only a masked 2D image and a natural language description presents significant challenges. The ROOMELSA challenge limits access to full 3D scene context, complicating reasoning about object appearance, geometry, and semantics. These challenges are intensified by distorted viewpoints, textureless masked regions, ambiguous language prompts, and noisy segmentation masks. To address this, we propose SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification. SAMURAI integrates CLIP-based semantic matching with shape-guided re-ranking derived from binary silhouettes of masked regions, alongside a robust majority voting strategy. A dedicated preprocessing pipeline enhances mask quality by extracting the largest connected component and removing background noise. Our hybrid retrieval framework leverages both language and shape cues, achieving competitive performance on the ROOMELSA private test set. These results highlight the importance of combining shape priors with language understanding for robust open-world 3D object retrieval.