2023/10/30 by Zhuoman Liu, Liu, Zhuoman, Bo Yang +4 · 3 citations
Computer Science · Engineering · Mathematics · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Algorithm #Artificial Intelligence (cs.AI) #Artificial intelligence #Classifier (UML) #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Consistency (knowledge bases) #Coordinate system #FOS: Computer and information sciences #Geography #Geometry #Graphics (cs.GR) #Machine Learning (cs.LG) #Mathematics #Point (geometry) #Representation (politics) #Robotics (cs.RO) #Surface (topology) #Visibility
paper · pdf · doi:10.48550/arxiv.2310.19629
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/10/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we study the problem of continuous 3D shape representations. The majority of existing successful methods are coordinate-based implicit neural representations. However, they are inefficient to render novel views or recover explicit surface points. A few works start to formulate 3D shapes as ray-based neural functions, but the learned structures are inferior due to the lack of multi-view geometry consistency. To tackle these challenges, we propose a new framework called RayDF. It consists of three major components: 1) the simple ray-surface distance field, 2) the novel dual-ray visibility classifier, and 3) a multi-view consistency optimization module to drive the learned ray-surface distances to be multi-view geometry consistent. We extensively evaluate our method on three public datasets, demonstrating remarkable performance in 3D surface point reconstruction on both synthetic and challenging real-world 3D scenes, clearly surpassing existing coordinate-based and ray-based baselines. Most notably, our method achieves a 1000x faster speed than coordinate-based methods to render an 800x800 depth image, showing the superiority of our method for 3D shape representation. Our code and data are available at https://github.com/vLAR-group/RayDF