Physics World Model — Modality Catalog

2 imaging modalities with descriptions, experimental setups, and reconstruction guidance.

3D Gaussian Splatting

gaussian_splatting Neural Rendering

3D Gaussian splatting represents scenes as a collection of learnable 3D Gaussian primitives, each parameterized by position, covariance (anisotropic 3D extent), opacity, and spherical harmonic color coefficients. Rendering rasterizes the Gaussians by projecting them to 2D screen space, sorting by depth, and alpha-compositing with a tile-based differentiable rasterizer. Training optimizes Gaussian parameters via gradient descent with adaptive density control (splitting, cloning, pruning). This achieves real-time (30+ fps) rendering at quality comparable to NeRF, from SfM point cloud initialization (COLMAP).

Physics: neural volume
Solver: gaussian_splatting_3dgs
Noise: gaussian
#neural_rendering #gaussian_splatting #3d #real_time #point_based
View details →

Neural Radiance Fields (NeRF)

nerf Neural Rendering

Neural radiance fields (NeRF) represent a 3D scene as a continuous volumetric function F(x,y,z,theta,phi) -> (RGB, sigma) parameterized by a multi-layer perceptron that maps 5D coordinates (position + viewing direction) to color and volume density. Novel views are synthesized by marching camera rays through the volume and integrating color weighted by transmittance using quadrature. Training optimizes the MLP weights to minimize photometric loss between rendered and observed images. Primary challenges include slow training/rendering, view-dependent effects, and the need for accurate camera poses (from COLMAP).

Physics: neural volume
Solver: nerf_mlp
Noise: gaussian
#neural_rendering #nerf #3d #view_synthesis #volumetric
View details →