NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
Top Cited Papers
Open Access
- 26 July 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (4) , 1-22
Abstract
We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment. Multiview reconstruction of reflective objects is extremely challenging because specular reflections are view-dependent and thus violate the multiview consistency, which is the cornerstone for most multiview reconstruction methods. Recent neural rendering techniques can model the interaction between environment lights and the object surfaces to fit the view-dependent reflections, thus making it possible to reconstruct reflective objects from multiview images. However, accurately modeling environment lights in the neural rendering is intractable, especially when the geometry is unknown. Most existing neural rendering methods, which can model environment lights, only consider direct lights and rely on object masks to reconstruct objects with weak specular reflections. Therefore, these methods fail to reconstruct reflective objects, especially when the object mask is not available and the object is illuminated by indirect lights. We propose a two-step approach to tackle this problem. First, by applying the split-sum approximation and the integrated directional encoding to approximate the shading effects of both direct and indirect lights, we are able to accurately reconstruct the geometry of reflective objects without any object masks. Then, with the object geometry fixed, we use more accurate sampling to recover the environment lights and the BRDF of the object. Extensive experiments demonstrate that our method is capable of accurately reconstructing the geometry and the BRDF of reflective objects from only posed RGB images without knowing the environment lights and the object masks. Codes and datasets are available at https://github.com/liuyuan-pal/NeRO.Keywords
This publication has 65 references indexed in Scilit:
- Shape, Illumination, and Reflectance from ShadingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Data-driven hallucination of different times of day from a single outdoor photoACM Transactions on Graphics, 2013
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Image-based rendering for scenes with reflectionsACM Transactions on Graphics, 2012
- Real-Time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid2010
- Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo2008
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- The rendering equation1986
- A Reflectance Model for Computer GraphicsACM Transactions on Graphics, 1982
- Theory for Off-Specular Reflection From Roughened Surfaces*Journal of the Optical Society of America, 1967