Run the pipelines

Apply transformations

In the previous section, you built the AI Camera Pipelines. In this section, you’ll run them to apply transformations to an input image or input frames.

    

        
        
cd $HOME/ai-camera-pipelines
python3 -m venv venv
. venv/bin/activate
pip install numpy opencv-python pillow torch

    

Background blur

Run the background Blur pipeline, using resources/test_input.png as the input image and write the transformed image to test_output_cinematic_mode.png:

    

        
        
cd $HOME/ai-camera-pipelines
bin/cinematic_mode resources/test_input.png test_output_cinematic_mode.png resources/depth_and_saliency_v3_2_assortedv2_w_augment_mobilenetv2_int8_only_ptq.tflite

    

Input image Image with blur applied

Low-Light Enhancement

Run the Low-Light Enhancement pipeline, using resources/test_input.png as the input image and write the transformed image to test_output_lime.png:

    

        
        
cd $HOME/ai-camera-pipelines
bin/low_light_image_enhancement resources/test_input.png test_output_lime.png resources/HDRNetLIME_lr_coeffs_v1_1_0_mixed_low_light_perceptual_l1_loss_float32.tflite

    

Input image Image with low-light enhancement applied

Neural denoising

When the SME extension is not available, only temporal neural denoising is available, so this is what you will run for now — but stay tuned as the SME extension will become available very soon:

    

        
        
./scripts/run_neural_denoiser_temporal.sh

    

The input frames are:

• first converted from .png files in the resources/test-lab-sequence/ directory to the sensor format (RGGB Bayer) into neural_denoiser_io/input_noisy*
• those frames are then processed by the Neural Denoiser and written into neural_denoiser_io/output_denoised*
• last, the denoised frames are converted back to .png for easy visualization in directory test-lab-sequence-out

Original frame Frame with temporal denoising applied