发表机构
State Key Laboratory of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出首个实时反射感知高斯SLAM系统，采用TSDF-高斯混合表示分离反射，通过三遍渲染和反射感知跟踪，在室内反射场景中实现优于现有方法的重建质量、跟踪鲁棒性和实时性能。
AI 中文摘要
我们首次提出了面向室内场景的实时反射感知高斯SLAM系统。该系统采用反射感知的TSDF-高斯混合表示，将漫反射场景外观与反射成分明确分离。基础场景由TSDF体素和一组基础高斯体建模，用于捕捉几何和漫反射外观，而平面反射则由与检测到的反射平面对应的反射高斯组表示。渲染分三遍进行：首先，TSDF光线投射生成表面颜色、深度、平面ID和反射掩码；然后，基础高斯体以顺序无关的方式渲染，并进行深度剔除，与TSDF输出结合形成基础图像；最后，在平面ID图的引导下，来自不同反射组的高斯体仅被光栅化到其对应的平面区域以生成反射图像，随后通过反射掩码与基础图像合成，产生最终输出。对于在线重建，我们的系统首先通过反射感知跟踪估计相机位姿，以抑制反射主导区域的干扰。然后，利用几何、语义和时间线索识别反射平面，并将观测融合到带有反射感知属性的增强TSDF体素中。之后，基础高斯体和反射高斯体在线初始化、优化和剪枝，以保持重建质量和效率。在多种数据集上的实验表明，在具有反射的室内环境中，我们的方法在重建质量、跟踪鲁棒性和新视角渲染方面优于现有SLAM系统，同时保持实时性能。
英文摘要
We introduce the first real-time reflection-aware Gaussian SLAM system for indoor scenes. The system features a reflection-aware TSDF-Gaussian hybrid representation that explicitly separates diffuse scene appearance from reflection components. The base scene is modeled by a TSDF volume and a set of base Gaussians capturing geometry and diffuse appearance, while planar reflections are represented by reflection Gaussian groups associated with detected reflective planes. The rendering is performed in three passes: TSDF raycasting first yields surface color, depth, plane IDs and reflection masks; base Gaussians are then rendered order-independently with depth culling and combined with the TSDF output to form the base image; finally, under the guidance of the plane ID map, reflection Gaussians from different reflection groups are rasterized only into their corresponding planar regions to generate the reflection image, which is subsequently composited with the base image via the reflection mask to produce the final output. For online reconstruction, our system first estimates the camera pose through reflection-aware tracking to suppress interference of reflection-dominated regions. It then identifies reflective planes using geometric, semantic, and temporal cues, and fuses the observations into the augmented TSDF volume with reflection-aware attributes. Afterwards the base and reflection Gaussians are initialized, optimized, and pruned online to maintain both reconstruction quality and efficiency. Experiments on a variety of datasets show that our method outperforms existing SLAM systems in reconstruction quality, tracking robustness, and novel-view rendering for indoor environments with reflections, while preserving real-time performance.
