LightSplat: 五秒内快速且内存高效的开放词汇3D场景理解
LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds
AI总结：
本文提出LightSplat框架，通过注入紧凑的2字语义索引实现快速且内存高效的开放词汇3D场景理解，实现50-400倍速度提升和64倍内存降低。
摘要：
开放词汇3D场景理解使用户能够通过自然语言在复杂3D环境中分割新物体。然而，现有方法因迭代优化和密集的每高斯特征分配而缓慢、内存密集且复杂。为此，我们提出LightSplat，一种快速且内存高效的无训练框架，将紧凑的2字语义索引注入多视角图像的3D表示中。通过仅将语义索引分配给显著区域，并使用轻量级索引-特征映射进行管理，LightSplat消除了昂贵的特征优化和存储开销。我们进一步通过单步聚类确保语义一致性和高效推理，该聚类将几何和语义相关的3D掩码链接起来。我们在LERF-OVS、ScanNet和DL3DV-OVS上评估了我们的方法，涵盖复杂的室内外场景。结果表明，LightSplat在性能上达到最先进的水平，实现了50-400倍的速度提升和64倍的内存降低，使语言驱动的3D理解成为可能。更多详情请访问我们的项目页面https://vision3d-lab.github.io/lightsplat/。
英文摘要：
Open-vocabulary 3D scene understanding enables users to segment novel objects in complex 3D environments through natural language. However, existing approaches remain slow, memory-intensive, and overly complex due to iterative optimization and dense per-Gaussian feature assignments. To address this, we propose LightSplat, a fast and memory-efficient training-free framework that injects compact 2-byte semantic indices into 3D representations from multi-view images. By assigning semantic indices only to salient regions and managing them with a lightweight index-feature mapping, LightSplat eliminates costly feature optimization and storage overhead. We further ensure semantic consistency and efficient inference via single-step clustering that links geometrically and semantically related masks in 3D. We evaluate our method on LERF-OVS, ScanNet, and DL3DV-OVS across complex indoor-outdoor scenes. As a result, LightSplat achieves state-of-the-art performance with up to 50-400x speedup and 64x lower memory, enabling scalable language-driven 3D understanding. For more details, visit our project page https://vision3d-lab.github.io/lightsplat/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
