Guardado en:
Detalles Bibliográficos
Autores principales: Tian, Lei, Li, Xiaomin, Ma, Liqian, Yin, Hao, Zheng, Zirui, Huang, Hefei, Li, Taiqing, Lu, Huchuan, Jia, Xu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.20469
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913990163038208
author Tian, Lei
Li, Xiaomin
Ma, Liqian
Yin, Hao
Zheng, Zirui
Huang, Hefei
Li, Taiqing
Lu, Huchuan
Jia, Xu
author_facet Tian, Lei
Li, Xiaomin
Ma, Liqian
Yin, Hao
Zheng, Zirui
Huang, Hefei
Li, Taiqing
Lu, Huchuan
Jia, Xu
contents Recent advances in 3D reconstruction techniques and vision-language models have fueled significant progress in 3D semantic understanding, a capability critical to robotics, autonomous driving, and virtual/augmented reality. However, methods that rely on 2D priors are prone to a critical challenge: cross-view semantic inconsistencies induced by occlusion, image blur, and view-dependent variations. These inconsistencies, when propagated via projection supervision, deteriorate the quality of 3D Gaussian semantic fields and introduce artifacts in the rendered outputs. To mitigate this limitation, we propose CCL-LGS, a novel framework that enforces view-consistent semantic supervision by integrating multi-view semantic cues. Specifically, our approach first employs a zero-shot tracker to align a set of SAM-generated 2D masks and reliably identify their corresponding categories. Next, we utilize CLIP to extract robust semantic encodings across views. Finally, our Contrastive Codebook Learning (CCL) module distills discriminative semantic features by enforcing intra-class compactness and inter-class distinctiveness. In contrast to previous methods that directly apply CLIP to imperfect masks, our framework explicitly resolves semantic conflicts while preserving category discriminability. Extensive experiments demonstrate that CCL-LGS outperforms previous state-of-the-art methods. Our project page is available at https://epsilontl.github.io/CCL-LGS/.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20469
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting
Tian, Lei
Li, Xiaomin
Ma, Liqian
Yin, Hao
Zheng, Zirui
Huang, Hefei
Li, Taiqing
Lu, Huchuan
Jia, Xu
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advances in 3D reconstruction techniques and vision-language models have fueled significant progress in 3D semantic understanding, a capability critical to robotics, autonomous driving, and virtual/augmented reality. However, methods that rely on 2D priors are prone to a critical challenge: cross-view semantic inconsistencies induced by occlusion, image blur, and view-dependent variations. These inconsistencies, when propagated via projection supervision, deteriorate the quality of 3D Gaussian semantic fields and introduce artifacts in the rendered outputs. To mitigate this limitation, we propose CCL-LGS, a novel framework that enforces view-consistent semantic supervision by integrating multi-view semantic cues. Specifically, our approach first employs a zero-shot tracker to align a set of SAM-generated 2D masks and reliably identify their corresponding categories. Next, we utilize CLIP to extract robust semantic encodings across views. Finally, our Contrastive Codebook Learning (CCL) module distills discriminative semantic features by enforcing intra-class compactness and inter-class distinctiveness. In contrast to previous methods that directly apply CLIP to imperfect masks, our framework explicitly resolves semantic conflicts while preserving category discriminability. Extensive experiments demonstrate that CCL-LGS outperforms previous state-of-the-art methods. Our project page is available at https://epsilontl.github.io/CCL-LGS/.
title CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.20469