PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction
This addresses a specific problem in computer vision for applications like robotics or inspection, but it is incremental as it builds on existing neural SDF frameworks.
The paper tackles the challenge of 3D reconstruction for reflective and textureless surfaces by proposing PMNI, a neural method that uses surface normal maps to recover camera poses and geometry, achieving state-of-the-art performance on synthetic and real-world datasets.
Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues, we present PMNI (Pose-free Multi-view Normal Integration), a neural surface reconstruction method that incorporates rich geometric information by leveraging surface normal maps instead of RGB images. By enforcing geometric constraints from surface normals and multi-view shape consistency within a neural signed distance function (SDF) optimization framework, PMNI simultaneously recovers accurate camera poses and high-fidelity surface geometry. Experimental results on synthetic and real-world datasets show that our method achieves state-of-the-art performance in the reconstruction of reflective surfaces, even without reliable initial camera poses.