dlp-26t2-nppe3-lowlight-denoise-sr

Low-light Joint Denoising + ×4 Super-Resolution (NAFNet-UNet)

Models for the Kaggle competition DLP 26T2 NPPE3 (dlp-26t2-nppe3). Roll number 23f1001168.

Task

Recover a clean 1024×640 image from a noisy, low-light 256×160 observation of a street scene (Cityscapes-like). The competition metric is PSNR on the grayscale (PIL convert('L')) version of the 1024×640 output, sampled at every 8th pixel.

The degradation, reverse-engineered

Comparing each provided LR image against an area-downsample of its ground truth showed the residual variance is linear in intensity, with matching skewness:

var(residual) = 2.526 * I + 1.49        (per channel, mutually independent)

which is pure Poisson shot noise with gain g = 2.526 and negligible read noise. The full forward model is

LR = floor( g * Poisson( area_downsample_4x(HR) / g ) )   clipped to [0, 255]

Training a model only on noise synthesised with this model scores the same as training on the organisers' real LR images (38.960 vs 38.953 dB), which confirms the model is correct — and makes the noise an unlimited augmentation.

Architecture

DenoiseSRNet — a NAFNet U-Net over the LR grid followed by a ×4 PixelShuffle head. The network predicts a residual on top of a blurred-and-bicubic-upsampled luma, so it only has to model denoising and high-frequency detail. It outputs a single luma channel, matching the metric exactly rather than wasting capacity on colour.

Results (267-image validation split)

The oracle row shows denoising, not upsampling, is what the task is really about.

⚠️ These are small models (32-width, 12k iterations each) trained as an ablation sweep, not a long production run. The architecture scales well beyond this.

Files

• model_*.pt — checkpoints; each holds ema, model, and the args needed to rebuild the net
• model.py, common.py, train.py, predict.py, make_submission.py — full pipeline
• manifest.json — per-checkpoint config and validation score

Usage

import torch, numpy as np
from predict import load_net, infer

net, cfg = load_net("model_3_ab_mse.pt", "cuda")     # cfg comes from the checkpoint
lr = np.array(Image.open("test_00001.png"))[None]    # (1,160,256,3) uint8
hr_luma = infer([net], [cfg], lr, "cuda", tta=True)  # (1,640,1024) float32, 0..255