用渐进式高斯+自适应采样，实现开放词汇3D占位预测新精度
Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction
- 分阶段在线加密高斯表示，逐步提升细节捕捉能力
- 引入各向异性感知采样，提升不同尺度下特征聚合效率
- 在真实场景中实现14.3%的mIoU提升，适合自动驾驶应用
3D占位预测近年来发展迅速，在基于视觉的自动驾驶系统中扮演关键角色。传统方法局限于固定语义类别，而近期方法转向文本对齐特征预测，支持开放词汇文本查询。然而，文本对齐建模存在权衡：稀疏高斯表示难以捕捉小物体，密集表示则计算开销大。为此，我们提出PG-Occ——一种创新的渐进式高斯变换框架，实现开放词汇3D占位预测。该框架采用渐进式在线加密策略，通过前馈方式逐步增强3D高斯表示以捕捉精细场景细节，实现更精确的场景理解。另一核心贡献是引入各向异性感知采样与时空融合机制，自适应地为不同尺度和阶段的高斯分配感受野，实现更高效的特征聚合和更丰富的场景信息捕获。大量实验表明，PG-Occ相较此前最佳方法实现14.3%的相对mIoU提升。代码与预训练模型将在发布后于项目页面公开：https://yanchi-3dv.github.io/PG-Occ
原文摘要 · Abstract (English)
The 3D occupancy prediction task has witnessed remarkable progress in recent years, playing a crucial role in vision-based autonomous driving systems. While traditional methods are limited to fixed semantic categories, recent approaches have moved towards predicting text-aligned features to enable open-vocabulary text queries in real-world scenes. However, there exists a trade-off in text-aligned scene modeling: sparse Gaussian representation struggles to capture small objects in the scene, while dense representation incurs significant computational overhead. To address these limitations, we present PG-Occ, an innovative Progressive Gaussian Transformer Framework that enables open-vocabulary 3D occupancy prediction. Our framework employs progressive online densification, a feed-forward strategy that gradually enhances the 3D Gaussian representation to capture fine-grained scene details. By iteratively enhancing the representation, the framework achieves increasingly precise and detailed scene understanding. Another key contribution is the introduction of an anisotropy-aware sampling strategy with spatio-temporal fusion, which adaptively assigns receptive fields to Gaussians at different scales and stages, enabling more effective feature aggregation and richer scene information capture. Through extensive evaluations, we demonstrate that PG-Occ achieves state-of-the-art performance with a relative 14.3% mIoU improvement over the previous best performing method. Code and pretrained models will be released upon publication on our project page: https://yanchi-3dv.github.io/PG-Occ
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。