SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearization
This addresses the challenge of efficient 3D reconstruction for applications like computer vision and graphics, representing an incremental improvement over existing methods.
The paper tackles the problem of 3D shape and appearance reconstruction from a few colored images, achieving state-of-the-art performance in novel-view synthesis and reconstruction from sparse views on standard benchmarks with training times under 10 minutes.
We present a novel approach for recovering 3D shape and view dependent appearance from a few colored images, enabling efficient 3D reconstruction and novel view synthesis. Our method learns an implicit neural representation in the form of a Signed Distance Function (SDF) and a radiance field. The model is trained progressively through ray marching enabled volumetric rendering, and regularized with learning-free multi-view stereo (MVS) cues. Key to our contribution is a novel implicit neural shape function learning strategy that encourages our SDF field to be as linear as possible near the level-set, hence robustifying the training against noise emanating from the supervision and regularization signals. Without using any pretrained priors, our method, called SparseCraft, achieves state-of-the-art performances both in novel-view synthesis and reconstruction from sparse views in standard benchmarks, while requiring less than 10 minutes for training.