SESQ: Spatially Aware Encoding and Semantically Guided Querying for 3D Grounding
Computers · 01.03.2026 · 15 (3) · 145
DOI: 10.3390/computers15030145 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers, online erschienen am 01.03.2026. Verfasst von Jinyuan Li und 3 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province, China, Xiamen City’s Leading Project.
Abstract (Originalsprache)
3D visual grounding is a fundamental task for human–machine interaction, aiming to localize specific objects in complex 3D point clouds based on natural language descriptions. Despite recent advancements, existing Transformer-based architectures often rely on absolute position embeddings and heuristic query initialization, which lack the capacity to capture fine-grained relative spatial dependencies and fail to effectively filter out scene clutter. In this paper, we propose SESQ, a novel framework that synergizes Spatially Aware Encoding and Semantically Guided Querying for 3D grounding. Our approach introduces two key innovations. First, we propose the Rotary Spatially Aware Encoder (RSAE), which incorporates Rotary Position Embeddings (RoPE) into the self-attention layers. By transforming 3D coordinates into a rotary representation, RSAE enables the model to inherently capture relative spatial distances and maintains geometric consistency throughout the encoding stage. Second, a Semantic Query Initialization (SQI) module is designed to initialize object queries by explicitly computing the cross-modal similarity between textual embeddings and visual point cloud features. By replacing traditional heuristic-based selection with semantic-aware alignment, SQI ensures that the decoding process originates from contextually relevant object candidates, significantly reducing the impact of task-irrelevant distractors. Extensive experiments on ScanRefer and ReferIt3D (Nr3D/Sr3D) benchmarks demonstrate the effectiveness of our framework. Compared to the baseline EDA, our method achieves a significant performance gain of 2.68% in overall Acc@0.5 on ScanRefer, a 4.9% improvement on the challenging Nr3D “Hard” subset, and a 1.1% increase in overall Acc@0.25 on Sr3D.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Fujian Province, China
- Xiamen City’s Leading Project
- Natural Science Foundation of Xiamen, China
- Open Competition for Innovative Projects of Xiamen
Zitieren
APA
Li, J., Wu, Y., Huang, T., & Cao, M. (2026). SESQ: Spatially Aware Encoding and Semantically Guided Querying for 3D Grounding. Computers, 15(3), 145. https://doi.org/10.3390/computers15030145
Vancouver
Li J, Wu Y, Huang T, Cao M. SESQ: Spatially Aware Encoding and Semantically Guided Querying for 3D Grounding. Computers. 2026;15(3):145. doi:10.3390/computers15030145
BibTeX
@article{Li2026,
author = {Li, Jinyuan and Wu, Yundong and Huang, Tiancai and Cao, Mengyun},
title = {SESQ: Spatially Aware Encoding and Semantically Guided Querying for 3D Grounding},
journal = {Computers},
year = {2026},
volume = {15},
number = {3},
pages = {145},
doi = {10.3390/computers15030145}
}
EUVIMED