Expand description
3DGS trainer.
Re-exports§
pub use crate::dataset::sparse_view;
pub use crate::dataset::SparseViewDataset;
pub use crate::error::Error;
pub use crate::metric;
pub use crate::metric::Metric;
pub use crate::optimize::Adam;
pub use crate::optimize::AdamRecord;
pub use crate::optimize::LearningRate;
pub use crate::optimize::LearningRateRecord;
pub use config::*;
pub use refine::*;
Modules§
- Burn Autodiff
- Backend module.
- 3DGS trainer configuration.
- Types and traits of JIT backend.
- 3DGS refinement implementation.
Structs§
- 3DGS rendering options.
- 3DGS rendering output (autodiff enabled).
- 3DGS representation.
- Trainer for 3DGS.
- Trainer record for 3DGS.
- The record item type for the module.
- Generic tensor backend that can be compiled just-in-time to any shader runtime
- A tensor with a given backend, shape and data type.
- Runtime that uses the [wgpu] crate with the wgsl compiler. This is used in the Wgpu backend. For advanced configuration, use [
init_sync
] to pass in runtime options or to select a specific graphics API.
Enums§
- The device struct when using the
wgpu
backend.
Constants§
- 3DGS default seed.
Traits§
- Trait that allows a backend to support autodiff.
- Module with auto-differentiation backend.
- This trait defines all types and functions needed for a backend to be used with burn.
- Configuration trait.
- 3DGS scene renderer.
- Trait to define a family of types which can be recorded using any settings.
Type Aliases§
- The backend marker to enable autodiff.
- The JIT backend using
WgpuRuntime
.
Derive Macros§
- Derive macro for the config.
- Derive macro for the record.