projects/lumigrid

LumiGrid

Computer visionResearch prototype

Low-light image enhancement that predicts a luminance-guided bilateral grid of Zero-DCE curves and colour matrices from a thumbnail of the whole image, slices it at full resolution, and cleans noise and detail with a lightweight NAFNet refiner. Rebuilt from an earlier course project on the NTIRE 2025 challenge data.

Evidence

On 20 held-out NTIRE 2025 pairs with the official scoring code: 24.57 dB PSNR / 0.840 SSIM (24.63 dB with test-time augmentation), against 16.48 dB for the original Zero-DCE course pipeline and 20.91 dB for Zero-DCE trained on the same data; component ablations, released weights, 2.1 M parameters, 24-megapixel images on an 8 GB laptop GPU.

Open the interactive portfolio →Try it in your browser Watch the film Source ↗Results and ablations ↗

This is a lightweight page for sharing. The full, interactive version lives in the terminal portfolio.