kornia: AugmentationSequential does not return lists of boxes

Describe the bug

When passing boxes as lists of tensors with any BBOX datakey to AugmentationSequential the resulting augmentation is not returned. Thus, the returned outputs have one fewer element than the inputs that were passed to it. This happens for both forward and inverse.

Reproduction steps

import kornia.augmentation as K
import torch

img = torch.rand((3,3,10,10))
bbox = [torch.tensor([[1,5,2,7],[0,3,9,9]]),torch.tensor([[1,5,2,7],[0,3,9,9],[0,5,8,7]]), torch.empty((0,4))]
inputs = [img, bbox]

aug = K.AugmentationSequential(K.Resize((300,300)), data_keys=['input', 'bbox_xyxy'])

transformed = aug(*inputs)

assert len(transformed) == len(inputs)

Traceback (most recent call last):             
  File "/home/miquelmr/kornia/test.py", line 12, in <module>
    assert len(transformed) == len(inputs)
AssertionError  

Expected behavior

List of boxes is returned.

Environment

Collecting environment information...
PyTorch version: 1.13.0+cu117
Is debug build: False
CUDA used to build PyTorch: 11.7
ROCM used to build PyTorch: N/A

OS: Ubuntu 18.04.6 LTS (x86_64)
GCC version: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.27

Python version: 3.10.8 (main, Nov 24 2022, 14:13:03) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-4.15.0-196-generic-x86_64-with-glibc2.27
Is CUDA available: True
CUDA runtime version: Could not collect
GPU models and configuration: 
GPU 0: NVIDIA TITAN X (Pascal)
GPU 1: NVIDIA TITAN X (Pascal)
GPU 2: NVIDIA TITAN Xp

Nvidia driver version: 520.61.05
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A

Versions of relevant libraries:
[pip3] numpy==1.23.5
[pip3] torch==1.13.0
[pip3] torchvision==0.14.0
[conda] numpy                     1.23.5                   pypi_0    pypi
[conda] torch                     1.13.0                   pypi_0    pypi
[conda] torchvision               0.14.0                   pypi_0    pypi

Additional context

No response