Simplicits: Mesh-Free, Geometry-Agnostic, Elastic Simulation
Simplicits: Mesh-free volumetric simulation of objects represented by explicit triangle meshes, point clouds, implicit functions, Computed Tomography volumes,NeRFs, and Gaussian Splats, all produced using our data-free neural fields-based simulation algorithm. Here we show frames from 60 of the 140+ simulations performed. The proliferation of 3D representations, from explicit meshes to implicit neural fields and more, motivates the need for simulators agnostic to rep- resentation. We present a data-, mesh-, and grid-free solution for elastic simulation for any object in any geometric representation undergoing large, nonlinear deformations. We note that every standard geometric representa- tion can be reduced to an occupancy function queried at any point in space, and we define a simulator atop this common interface. For each object, we fit a small implicit neural network encoding spatially varying weights that act as a reduced deformation basis. These weights are trained to learn physi
1 University of Toronto 2 NVIDIA 3 Texas A&M University Simplicits: Mesh-free volumetric simulation of objects represented by explicit triangle meshes, point clouds, implicit functions, Computed Tomography volumes,NeRFs, and Gaussian Splats, all produced using our data-free neural fields-based simulation algorithm. Here we show frames from 60 of the 140+ simulations performed. Abstract The proliferation of 3D representations, from explicit meshes to implicit neural fields and more, motivates the need for simulators agnostic to rep- resentation. We present a data-, mesh-, and grid-free…
saved by
related reading
- Fast Complementary Dynamicsdgp.toronto.edu
- S4Darxiv.org
- Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidsarxiv.org
- 3D Gaussian Splatting as Markov Chain Monte Carloubc-vision.github.io
- Learning 3D object-centric representation through predictionarxiv.org
- DyniBararxiv.org
- 3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimationarxiv.org
- 3D Object Detection via 2D Segmentation-Based Computational Integral Imaging Applied to a Real Videoncbi.nlm.nih.gov
- NeRF: Neural Radiance Fieldsmatthewtancik.com
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation | PDFarxiv.org
- Native and Compact Structured Latents for 3D Generationmicrosoft.github.io
- D-NeRF: Neural Radiance Fields for Dynamic Scenesopenaccess.thecvf.com