MoReMouse: Monocular Reconstruction of Laboratory Mouse
This addresses a domain-specific problem for biomedical researchers by enabling dense 3D reconstruction of laboratory mice, which is incremental as it builds on prior work in monocular reconstruction but tailored to a new application.
They tackled the problem of accurate 3D mouse surface motion reconstruction from monocular images, which is challenging due to non-rigid deformations and textureless appearance, and achieved significant outperformance over existing methods in accuracy and robustness.
Laboratory mice play a crucial role in biomedical research, yet accurate 3D mouse surface motion reconstruction remains challenging due to their complex non-rigid geometric deformations and textureless appearance. Moreover, the absence of structured 3D datasets severely hinders the progress beyond sparse keypoint tracking. To narrow the gap, we present MoReMouse, the first monocular dense 3D reconstruction network tailored for laboratory mice. To achieve this goal, we highlight three key designs. First, we construct the first high-fidelity dense-view synthetic dataset for mice, by rendering our self-designed realistic Gaussian mouse avatar. Second, MoReMouse adopts a transformer-based feedforward architecture with triplane representation, achieving high-quality 3D surface generation from a single image. Third, we create geodesic-based continuous correspondence embeddings on mouse surface, which serve as strong semantic priors to improve reconstruction stability and surface consistency. Extensive quantitative and qualitative experiments demonstrate that MoReMouse significantly outperforms existing open-source methods in accuracy and robustness. Video results are available at https://zyyw-eric.github.io/MoreMouse-webpage/.