train.hpp File Reference

#include <reusex/gsplat/GaussianCloud.hpp>
#include <reusex/gsplat/TrainingViews.hpp>
#include <atomic>
#include <cstdint>
#include <filesystem>
#include <string>
#include <vector>

Include dependency graph for train.hpp:

Go to the source code of this file.

Classes
struct	reusex::gsplat::MCMCOptions
	3DGS-MCMC density control (Kheradmand et al. More...
struct	reusex::gsplat::TrainOptions
	Optimizer / schedule parameters for the 3DGS training loop. More...
struct	reusex::gsplat::TrainMetrics
	One row of the loss history. More...
struct	reusex::gsplat::EvalMetrics
	One held-out evaluation pass. More...
struct	reusex::gsplat::TrainResult
struct	reusex::gsplat::GsplatStageOptions
	End-to-end options for the rux create gsplat stage. More...

Namespaces
namespace	cv
namespace	reusex
namespace	reusex::gsplat

Functions
bool	reusex::gsplat::is_available ()
	True when this build actually contains the CUDA trainer.
bool	reusex::gsplat::has_cuda_device ()
	True when this process can actually reach a CUDA device right now.
TrainResult	reusex::gsplat::train_gaussians (const GaussianCloud &init, const std::vector< TrainingView > &views, const TrainOptions &opt={})
	Train Gaussians against posed views.
cv::Mat	reusex::gsplat::render_view (const GaussianCloud &gaussians, const TrainingView &view)
	Rasterize gaussians from view.
TrainResult	reusex::gsplat::run_gsplat_stage (ProjectDB &db, const GsplatStageOptions &opt)
	Load the seed cloud and views from db, train, and store the splat.