RawSLAM：基于线性辐射的在线HDR高斯SLAM
RawSLAM: Online HDR Gaussian SLAM from Linear Radiance
浏览论文内容
中文总结 AI 辅助
针对极端光照下LDR SLAM的鲁棒性问题，提出首个在线HDR高斯SLAM框架RawSLAM，直接处理16位线性图像，通过HDR高斯溅射、Reinhard光度目标和梯度加权，提升轨迹与重建精度，并引入包含10个序列的RAW数据集。
中文摘要 AI 辅助
当前的稠密视觉SLAM系统几乎完全依赖8位色调映射的低动态范围（LDR）输入，这限制了它们在极端光照条件下的鲁棒性，因为阴影和高光会导致跟踪漂移和建图崩溃。相反，现有的原始和高动态范围（HDR）重建流程严格离线运行，依赖运动恢复结构（Structure-from-Motion）预处理，且不适用于大的帧间运动。据我们所知，我们提出了首个在线高斯SLAM框架，可直接在单次曝光的16位线性HDR图像上进行跟踪和建图。我们的方法基于三个核心组件：一个与架构无关的HDR高斯溅射模块，采用无MLP的对数参数化高斯颜色特征；一个Reinhard范围压缩光度目标函数；以及结构引导的空间梯度加权。这些组件相结合，使我们的方法在轨迹和重建精度上均优于直接HDR适配的MonoGS，同时以线性场景辐射进行原生渲染，便于后期处理。相同的公式在标准8位输入上无需修改即可运行，大致将MonoGS基线误差减半。此外，我们的HDR高斯模块可无缝迁移到SplaTAM、Gaussian SLAM和DROID-W，消除了这些系统在具有挑战性的光照序列上遇到的所有跟踪失败。为支持这项研究，我们引入了RawSLAM：一个包含10个真实世界室内序列的数据集，具有16位RAW图像、对齐的深度、IMU测量和外部OptiTrack位姿。代码和数据集将很快公开。
英文摘要
Current dense visual SLAM systems rely almost exclusively on 8-bit tonemapped Low Dynamic Range (LDR) inputs, limiting their robustness in extreme lighting where shadows and highlights trigger tracking drift and mapping collapse. Conversely, existing raw and High Dynamic Range (HDR) reconstruction pipelines operate strictly offline. They depend on Structure-from-Motion preprocessing and are not suited for large inter-frame motion. We present, to the best of our knowledge, the first online Gaussian SLAM framework that tracks and maps directly on single-exposure 16-bit linear HDR imagery. Our method rests on three core components: an architecture-agnostic HDR Gaussian Splatting module featuring an MLP-free logarithmic parameterization of Gaussian color features; a Reinhard range-compressed photometric objective; and structure-guided spatial gradient weighting. Combined, these components allow our approach to outperform a direct HDR adaptation of MonoGS in both trajectory and reconstruction accuracy, while rendering natively in linear scene radiance for post-rendering processing. The same formulation runs unchanged on standard 8-bit inputs, roughly halving the MonoGS baseline error. Furthermore, our HDR Gaussian module transfers seamlessly to SplaTAM, Gaussian SLAM, and DROID-W, eliminating all tracking failures these systems suffer on challenging illumination sequences. To enable this research, we introduce RawSLAM: a dataset of 10 real-world indoor sequences featuring 16-bit RAW imagery, aligned depth, IMU measurements, and external OptiTrack poses. Code and dataset will be made publicly available soon.
