GenTri: Generative Triangulation for Occlusion-Robust 3D Mouse Pose Estimation

Markerless 3D mouse pose estimation enables scalable behavioral analysis in neuroscience, but occlusion remains a major challenge to reliable reconstruction across experimental environments. Limited annotated data make it difficult to handle diverse occlusion patterns through training alone. Applying pose estimation to hours-long behavioral recordings also requires efficient inference. We introduce GenTri, an inference-time framework combining multi-view geometry with a flow-matching pose prior. To reduce the influence of confidently incorrect detections under occlusion, GenTri replaces the $L_2$ reprojection objective with a redescending Cauchy objective. For efficiency, geometry-aware Gauss-Newton guidance determines each correction's direction and magnitude. This enables GenTri to match its first-order variant with $2\times$ (mouse) to $17\times$ (human) less guidance time. Across multiple 2D detectors and three mouse datasets spanning in-domain and out-of-domain environments, GenTri reduces reconstruction error under synthetic occlusion by 45% on average relative to the reconstruction method paired with each detector. The same guidance formulation extends to human pose benchmarks, demonstrating applicability beyond mouse pose estimation. See our Project page: [https://gentri-3dpose.github.io/](https://gentri-3dpose.github.io/).