2023 · 51 citations · 30 references
ComputingComputational Engineering3D ModelingComputer VisionNeural EngineeringDeep LearningGenerative ModelingImplicit ModelingNeural ModelingNeural NetworksDiffusion ModelsImplicit Generative ModelsMesh RepresentationMultilayer PerceptronNeural Representation LearningPerceptronRepresentation FidelitySignals
Implicit neural fields, typically encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to signals (e.g., signed distances), have shown remarkable promise as a high-fidelity and compact representation. However, the lack of a regular and explicit grid structure also makes it challenging to apply generative modeling directly on implicit neural fields in order to synthesize new data. To this end, we propose HyperDiffusion, a novel approach for unconditional generative modeling of implicit neural fields. HyperDiffusion operates directly on MLP weights and generates new neural implicit fields encoded by synthesized MLP parameters. Specifically, a collection of MLPs is first optimized to faithfully represent individual data samples. Subsequently, a diffusion process is trained in this MLP weight space to model the underlying distribution of neural implicit fields. HyperDiffusion enables diffusion modeling over a implicit, compact, and yet high-fidelity representation of complex signals across 3D shapes and 4D mesh animations within one single unified framework.
30
Generative adversarial networks
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza et al. · Communications of the ACM · 2020 · 13.6K citations · Full text
Marching cubes: A high resolution 3D surface construction algorithm
William E. Lorensen, H. E. Cline · 1987 · 10.2K citations · Full text
Computing, Radiology, Visualization +17
Decoupled Weight Decay Regularization
Ilya Loshchilov, Frank Hutter · arXiv (Cornell University) · 2017 · 9.1K citations · Full text
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik et al. · Communications of the ACM · 2021 · 5.8K citations · Full text