DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yani, Wu, Dongming, Shi, Hao, Liu, Yingfei, Wang, Tiancai, Dong, Xingping
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910170864418816
author Zhang, Yani
Wu, Dongming
Shi, Hao
Liu, Yingfei
Wang, Tiancai
Dong, Xingping
author_facet Zhang, Yani
Wu, Dongming
Shi, Hao
Liu, Yingfei
Wang, Tiancai
Dong, Xingping
contents A core task in embodied intelligence is ego-centric 3D visual grounding. Existing methods typically adopt two-stage, heterogeneous pipelines that pair a detector with a separate grounding model. Incompatible decoders and box heads hinder the transfer of object-level priors, and the split training causes redundant re-optimization. To overcome these limitations, we present DEGround, a straight, elegant, and effective framework that centers on object-level sharing over detection and grounding. It employs a set of queries that serves as the common object representation for both detection and grounding, which is decoded by a shared transformer and bounding box head. Building on this homogeneous framework, we further introduce two task-specific plug-in modules to enhance fine-grained instruction grounding. The Regional Activation Grounding module improves spatial-textual alignment by highlighting instruction-relevant regions, while the Query-wise Modulation module applies sentence-conditioned affine modulation to generate instruction-aware queries at initialization. Extensive experiments demonstrate that DEGround achieves the best performance on multiple benchmarks. Remarkably, it significantly outperforms previous methods by 7.52% at overall precision on the EmbodiedScan dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05199
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework
Zhang, Yani
Wu, Dongming
Shi, Hao
Liu, Yingfei
Wang, Tiancai
Dong, Xingping
Computer Vision and Pattern Recognition
A core task in embodied intelligence is ego-centric 3D visual grounding. Existing methods typically adopt two-stage, heterogeneous pipelines that pair a detector with a separate grounding model. Incompatible decoders and box heads hinder the transfer of object-level priors, and the split training causes redundant re-optimization. To overcome these limitations, we present DEGround, a straight, elegant, and effective framework that centers on object-level sharing over detection and grounding. It employs a set of queries that serves as the common object representation for both detection and grounding, which is decoded by a shared transformer and bounding box head. Building on this homogeneous framework, we further introduce two task-specific plug-in modules to enhance fine-grained instruction grounding. The Regional Activation Grounding module improves spatial-textual alignment by highlighting instruction-relevant regions, while the Query-wise Modulation module applies sentence-conditioned affine modulation to generate instruction-aware queries at initialization. Extensive experiments demonstrate that DEGround achieves the best performance on multiple benchmarks. Remarkably, it significantly outperforms previous methods by 7.52% at overall precision on the EmbodiedScan dataset.
title DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.05199