Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields

Miao, Xingyu; Duan, Haoran; Bai, Yang; Shah, Tejal; Song, Jun; Long, Yang; Ranjan, Rajiv; Shao, Ling

Abstract

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed and storage requirements, our approach aims to streamline the workflow by directly and effectively distilling dense CLIP features, thereby achieving precise segmentation of 3D scenes using text. To achieve this, we introduce an adapter module and mitigate the noise issue in the dense CLIP feature distillation process through a self-cross-training strategy. Moreover, to enhance the accuracy of segmentation edges, this work presents a low-rank transient query attention mechanism. To ensure the consistency of segmentation for similar colors under different viewpoints, we convert the segmentation task into a classification task through label volume, which significantly improves the consistency of segmentation in color-similar areas. We also propose a simplified text augmentation strategy to alleviate the issue of ambiguity in the correspondence between CLIP features and text. Extensive experimental results show that our method surpasses current state-of-the-art technologies in both training speed and performance. Our code is available on: https://github.com/xingy038/Laser.git.

Citation

Miao, X., Duan, H., Bai, Y., Shah, T., Song, J., Long, Y., Ranjan, R., & Shao, L. (online). Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, https://doi.org/10.1109/TPAMI.2025.3535916

• Journal Article Type: Article
• Acceptance Date: Jan 1, 2025
• Online Publication Date: Jan 29, 2025
• Deposit Date: Mar 6, 2025
• Publicly Available Date: Mar 11, 2025
• Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
• Print ISSN: 0162-8828
• Electronic ISSN: 1939-3539
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/TPAMI.2025.3535916
• Public URL: https://durham-repository.worktribe.com/output/3681375