Depth Estimators Are Implicit Neural Fields for 3D Scene Geometry Inpainting and Reconstruction
For 3D scene reconstruction and inpainting, NDF provides a unified solution to inconsistency and out-of-distribution issues, enabling high-fidelity geometry across diverse domains.
The paper tackles incomplete 3D scene geometry by proposing Neural Depth Field (NDF), which treats a depth estimator as an implicit neural field to simultaneously adapt to target domain and maintain consistency. NDF reduces cross-view inconsistency by 63.3% and improves inpainting accuracy by 23.1%, achieving state-of-the-art performance.
The 3D geometry of real-world scene data is often incomplete. Mainstream methods use depth estimators to inpaint missing structure. However, their prediction results can be inconsistent with observed geometry, or unreliable on out-of-distribution data. To solve these problems, we propose Neural Depth Field (NDF). Our key insight is that a depth estimator can also be a scene-level implicit field. As an estimator, it adapts to the target domain by learning observed depth data. As an implicit field, it fits the existing geometry to maintain consistency. Under this view, NDF addresses both problems through a single test-time optimization. Experiments show that NDF produces high-fidelity and globally consistent geometry across diverse scene data, ranging from indoor scans to satellite imagery. It reduces cross-view inconsistency by 63.3\% and improves inpainting accuracy by 23.1\%, achieving state-of-the-art performance in 3D scene geometry inpainting. The code is available at: https://github.com/Shadow-Dream/Neural-Depth-Field.