CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting

• URL: http://arxiv.org/abs/2505.20469v1
• Date: Mon, 26 May 2025 19:09:33 GMT
• Title: CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting
• Authors: Lei Tian, Xiaomin Li, Liqian Ma, Hefei Huang, Zirui Zheng, Hao Yin, Taiqing Li, Huchuan Lu, Xu Jia,
• Abstract summary: Methods that rely on 2D priors are prone to a critical challenge: cross-view semantic inconsistencies.<n>We propose CCL-LGS, a novel framework that enforces view-consistent semantic supervision by integrating multi-view semantic cues.<n>Our framework explicitly resolves semantic conflicts while preserving category discriminability.
• Score: 53.15827818829865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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/.

Related papers

• 3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap [10.744510913722817]
  3D-PointZshotS is a geometry-aware zero-shot segmentation framework.<n>We integrate LGPs into a generator via a cross-attention mechanism, enriching semantic features with fine-grained geometric details.<n>We re-present visual and semantic features in a shared space, bridging the semantic-visual gap and facilitating knowledge transfer to unseen classes.
  arXiv  Detail & Related papers  (2025-04-16T19:17:12Z)
• econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians [56.85804719947]
  We propose econSG for open-vocabulary semantic segmentation with 3DGS.<n>Our econSG shows state-of-the-art performance on four benchmark datasets compared to the existing methods.
  arXiv  Detail & Related papers  (2025-04-08T13:12:31Z)
• Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding [58.38294408121273]
  We propose Cross-modal and Uncertainty-aware Agglomeration for Open-vocabulary 3D Scene Understanding dubbed CUA-O3D.<n>Our method addresses two key challenges: (1) incorporating semantic priors from VLMs alongside the geometric knowledge of spatially-aware vision foundation models, and (2) using a novel deterministic uncertainty estimation to capture model-specific uncertainties.
  arXiv  Detail & Related papers  (2025-03-20T20:58:48Z)
• Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations? [55.99654128127689]
  Cross-modal contrastive distillation has recently been explored for learning effective 3D representations.<n>Existing methods focus primarily on modality-shared features, neglecting the modality-specific features during the pre-training process.<n>We propose a new framework, namely CMCR, to address these shortcomings.
  arXiv  Detail & Related papers  (2024-12-12T06:09:49Z)
• CLIP-GS: CLIP-Informed Gaussian Splatting for Real-time and View-consistent 3D Semantic Understanding [32.76277160013881]
  We present CLIP-GS, which integrates semantics from Contrastive Language-Image Pre-Training (CLIP) into Gaussian Splatting. SAC exploits the inherent unified semantics within objects to learn compact yet effective semantic representations of 3D Gaussians. We also introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.
  arXiv  Detail & Related papers  (2024-04-22T15:01:32Z)
• Segment Any 3D Object with Language [58.471327490684295]
  We introduce Segment any 3D Object with LanguagE (SOLE), a semantic geometric and-aware visual-language learning framework with strong generalizability. Specifically, we propose a multimodal fusion network to incorporate multimodal semantics in both backbone and decoder. Our SOLE outperforms previous methods by a large margin on ScanNetv2, ScanNet200, and Replica benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T17:59:10Z)
• Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation [114.72734384299476]
  We propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. We leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Our approach significantly boosts the capacity of segmentation models for unseen classes.
  arXiv  Detail & Related papers  (2024-03-13T11:23:55Z)
• OV-NeRF: Open-vocabulary Neural Radiance Fields with Vision and Language Foundation Models for 3D Semantic Understanding [9.25233177676278]
  OV-NeRF exploits potential of pre-trained vision and language foundation models to enhance semantic field learning. Our approach achieves a significant improvement of 20.31% and 18.42% in mIoU metric on Replica and ScanNet, respectively.
  arXiv  Detail & Related papers  (2024-02-07T08:19:57Z)
• Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation [17.914290294935427]
  Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set. Large-scale visual-language pre-trained models, such as CLIP, have shown their generalization ability in the zero-shot 2D vision tasks. We propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder.
  arXiv  Detail & Related papers  (2023-12-12T12:35:59Z)
• Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation [25.070027668717422]
  Generalized zero-shot semantic segmentation (GZS3) predicts pixel-wise semantic labels for seen and unseen classes. Most GZS3 methods adopt a generative approach that synthesizes visual features of unseen classes from corresponding semantic ones. We propose a discriminative approach to address limitations in a unified framework.
  arXiv  Detail & Related papers  (2021-08-14T13:33:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.