Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions
Authors:
Top Cited Papers
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2262-2272
Abstract
Probabilistic diffusion models have achieved state-of-the-art results for image synthesis, inpainting, and text-to-image tasks. However, they are still in the early stages of generating complex 3D shapes. This work proposes Diffusion-SDF, a generative model for shape completion, single-view reconstruction, and reconstruction of real-scanned point clouds. We use neural signed distance functions (SDFs) as our 3D representation to parameterize the geometry of various signals (e.g., point clouds, 2D images) through neural networks. Neural SDFs are implicit functions and diffusing them amounts to learning the reversal of their neural network weights, which we solve using a custom modulation module. Extensive experiments show that our method is capable of both realistic unconditional generation and conditional generation from partial inputs. This work expands the domain of diffusion models from learning 2D, explicit representations, to 3D, implicit representations. Code is released at https://github.com/princeton-computational-imaging/Diffusion-SDF.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- Convolutional Occupancy Networks2020
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Multimodal Shape Completion via Conditional Generative Adversarial Networks2020
- A Survey on Learning-Based Robotic GraspingCurrent Robotics Reports, 2020
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- A Papier-Mache Approach to Learning 3D Surface Generation2018
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image2017
- Machine learning–based 3‐D geometry reconstruction and modeling of aortic valve deformation using 3‐D computed tomography imagesInternational Journal for Numerical Methods in Biomedical Engineering, 2016
- Deep Residual Learning for Image Recognition2016
- A Survey of 3D Face Recognition Methods2005