DPA-Net: Structured 3D Abstraction from Sparse Views via Differentiable Primitive Assembly
Abstract
We present a differentiable rendering framework to learn structured 3D abstractions in the form of primitive assemblies from sparse RGB images capturing a 3D object. By leveraging differentiable volume rendering, our method does not require 3D supervision. Architecturally, our network follows the general pipeline of an image-conditioned neural radiance field (NeRF) exemplified by pixelNeRF for color prediction. As our core contribution, we introduce differential primitive assembly (DPA) into NeRF to output a 3D occupancy field in place of density prediction, where the predicted occupancies serve as opacity values for volume rendering. Our network, coined DPA-Net, produces a union of convexes, each as an intersection of convex quadric primitives, to approximate the target 3D object, subject to an abstraction loss and a masking loss, both defined in the image space upon volume rendering. With test-time adaptation and additional sampling and loss designs aimed at improving the accuracy and compactness of the obtained assemblies, our method demonstrates superior performance over state-of-the-art alternatives for 3D primitive abstraction from sparse views.
Más información
Título según WOS: | ID WOS:001352822700026 Not found in local WOS DB |
Título de la Revista: | COMPUTER VISION - ECCV 2024, PT LXXX |
Volumen: | 15138 |
Editorial: | SPRINGER INTERNATIONAL PUBLISHING AG |
Fecha de publicación: | 2025 |
Página de inicio: | 454 |
Página final: | 471 |
DOI: |
10.1007/978-3-031-72989-8_26 |
Notas: | ISI |