We show texture editing results demonstrating that our method offers a more intuitive editing approach, capable of modifying the material without changing the shading.

Abstract

The advancements in neural rendering have increased the need for techniques that enable intuitive editing of 3D objects represented as neural implicit surfaces. This paper introduces a novel neural algorithm for parameterizing neural implicit surfaces to simple parametric domains like spheres and polycubes. Our method allows users to specify the number of cubes in the domain, learning a configuration that closely resembles the target 3D object's geometry. It computes bi-directional deformation between the object and the domain using a forward mapping from the object's zero level set and an inverse deformation for backward mapping. We ensure near-bijective mapping with a cycle loss and optimize deformation smoothness. The parameterization quality, assessed by angle and area distortions, is guaranteed using a Laplacian regularizer and an optimized learned parametric domain. Our framework integrates with existing neural rendering pipelines, using multi-view images of a single object or multiple objects of similar geometries to reconstruct 3D geometry and compute texture maps automatically, eliminating the need for any prior information. We demonstrate the method's effectiveness on images of human heads and man-made objects.

Supplementary Video

Method

Results

Citation

@inproceedings{xu2024neuparam,
    title={Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering},
    author={Xu, Baixin and Hu, Jiangbei and Hou, Fei and Lin, Kwan-Yee and Wu, Wayne and Qian, Chen and He, Ying},
    booktitle={ECCV},
    year={2024}
    }
               

Acknowledgements

The website template was borrowed from Michaël Gharbi.