Query Rewriting for Complex Object Segmentation in 4D Gaussian Representations

2026-09-02

AI Summary

该研究针对4D高斯表示中冗长查询导致的噪声问题，提出一种无需训练的查询重写策略，通过转化为简洁关键词形式提高复杂对象分割性能。

Abstract

Recent 4D Gaussian representation frameworks have demonstrated strong performance in language-guided dynamic scene understanding. However, these methods remain highly sensitive to verbose and narrative-style queries that contain noisy contextual information. In this paper, we investigate the impact of query rewriting for complex object segmentation in 4D Gaussian representations. Inspired by recent findings in retrieval-augmented language models and keyword-guided query reformulation, we propose a training-free reinterpretation strategy that transforms long descriptive queries into concise keyword-grounded forms. Our approach progressively reduces linguistic noise while preserving semantic anchors relevant to object-centric representations. Experiments on HyperNeRF and Neu3D demonstrate that concise rewritten queries significantly improve both temporal localization and spatial segmentation performance. In particular, our method improves average temporal accuracy from 60.92% to 92.21% and average vIoU from 20.08% to 76.94% without any additional fine-tuning. Extensive ablation studies further reveal that shorter, keyword-focused queries consistently yield stable video-feature similarity distributions and better alignment with object-centric Gaussian representations

Problem

• 4D Gaussian Representations
• Query Rewriting
• Complex Object Segmentation
• Noisy Contextual Information

Innovation

• query rewriting
• 4D Gaussian representations
• keyword-grounded forms
• temporal localization
• spatial segmentation