Albumentations to Kornia Transform Mapping

On this page

• Migration Rules
• Color and Pixel Transforms
• Illumination, Weather, and Procedural Effects
• Geometric Transforms
• Dropout and Annotation-Aware Transforms
• Channel Notes
• Migration Example
• Benchmark Pages

This page maps Albumentations transforms to Kornia equivalents where Kornia has a direct benchmark implementation. The benchmark source of truth is benchmark/transforms/kornia_impl.py, with shared canonical parameters in benchmark/transforms/specs.py.

If the Kornia column is -, the benchmark has no direct Kornia implementation for that Albumentations transform. Kornia still has useful lower-level tensor and geometry APIs; the table is about direct augmentation primitives used by the benchmark.

Migration Rules

• Albumentations expects NumPy arrays, usually per sample as H,W,C.
• Kornia expects PyTorch tensors, usually batched as B,C,H,W.
• Kornia often exposes same_on_batch, p_batch, align_corners, keepdim, and tensor interpolation settings.
• Albumentations exposes target-aware behavior through A.Compose.
• RGB/color-space transforms are not arbitrary-channel transforms in either library.

Color and Pixel Transforms

Illumination, Weather, and Procedural Effects

Geometric Transforms

Dropout and Annotation-Aware Transforms

Channel Notes

Kornia and Albumentations can both operate on non-RGB tensors/arrays for many channel-agnostic transforms. The trap is color semantics: RGBShift, HueSaturationValue, ColorJitter, PlanckianJitter, RandomRain, and RandomSnow are RGB/color transforms.

Blur, crop, resize, flip, affine, perspective, noise, dropout, and normalization are usually safer for arbitrary-channel data. For medical, hyperspectral, remote-sensing, or sensor-fusion inputs, document whether each channel is exchangeable, geometric-only, or color-like before choosing transforms.

Migration Example

import albumentations as A

pipeline = A.Compose([
    A.HorizontalFlip(p=0.5),
    A.Rotate(angle_range=(-15, 15), p=0.5),
    A.GaussNoise(std_range=(0.05, 0.2), p=0.2),
])

For annotation-aware pipelines:

pipeline = A.Compose(
    [
        A.RandomCrop(height=512, width=512, p=1.0),
        A.HorizontalFlip(p=0.5),
    ],
    bbox_params=A.BboxParams(coord_format="pascal_voc", label_fields=["labels"]),
)

Benchmark Pages

• Kornia benchmark route
• Benchmark transform implementations