DFRNet-v1 Baseline
==================

OVERVIEW
--------

DFRNet-v1 is a lightweight convolutional image-to-image network
developed as a baseline for image restoration experiments.

The model takes an RGB image as input and transforms it through
convolutional feature extraction layers.

The encoder progressively changes the channel representation:

    RGB Input
        3 channels
            |
            v
        9 channels
            |
            v
        27 channels
            |
            v
        3 channels

The resulting three-channel representation is passed to the decoder.

The decoder uses bilinear interpolation to resize the output to:

    Height: 640 pixels
    Width:  1024 pixels


ARCHITECTURE
------------

Input RGB Image
        |
        v

Encoder
    |
    +-- ConvBlock: 3 -> 9
    |
    +-- ConvBlock: 9 -> 27
    |
    +-- Conv2D: 27 -> 3

        |
        v

Decoder
    |
    +-- Bilinear Upsampling
        Output: 640 x 1024

        |
        v

Reconstructed Output Image


CONVBLOCK
---------

Each ConvBlock contains:

    Conv2D (3x3)
        |
        v
    ReLU
        |
        v
    Conv2D (3x3)
        |
        v
    ReLU


MODEL STATISTICS
----------------

Total Parameters:
    10,524

Trainable Parameters:
    10,524


PYTORCH MODEL
-------------

ImageRegressionNet(
  (encoder): Encoder(
    (stage_1): ConvBlock(
      (block): Sequential(
        (0): Conv2d(3, 9, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU(inplace=True)
        (2): Conv2d(9, 9, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): ReLU(inplace=True)
      )
    )
    (stage_2): ConvBlock(
      (block): Sequential(
        (0): Conv2d(9, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (1): ReLU(inplace=True)
        (2): Conv2d(27, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (3): ReLU(inplace=True)
      )
    )
    (stage_3): Conv2d(27, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  )
  (decoder): Decoder(
    (upsample_block): Upsample(size=(640, 1024), mode='bilinear')
  )
  (encoder_decoder): Sequential(
    (0): Encoder(
      (stage_1): ConvBlock(
        (block): Sequential(
          (0): Conv2d(3, 9, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (1): ReLU(inplace=True)
          (2): Conv2d(9, 9, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (3): ReLU(inplace=True)
        )
      )
      (stage_2): ConvBlock(
        (block): Sequential(
          (0): Conv2d(9, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (1): ReLU(inplace=True)
          (2): Conv2d(27, 27, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
          (3): ReLU(inplace=True)
        )
      )
      (stage_3): Conv2d(27, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    )
    (1): Decoder(
      (upsample_block): Upsample(size=(640, 1024), mode='bilinear')
    )
  )
)