ICAT 2026 · Computer Vision

NO-FOG-NET
See Through
The Invisible

Real-time fog removal for autonomous vehicles powered by deep learning with CBAM attention

0
Dataset Images
0
Downloads
0
Parameters
0
Latency
Dense Fog
Scroll to clear the fog
The Problem

Fog blinds autonomous
vehicles. We fix that.

Fog causes hundreds of fatal crashes yearly. NO-FOG-NET restores visual clarity in under 50ms — fast enough for real autonomous driving decisions at the edge.

01

Hazy Input

Camera captures foggy scene. Visibility severely degraded, edges lost, depth ambiguous.

02

CBAM Attention

Channel and spatial attention modules identify which features matter most for haze removal.

03

Inference

Lightweight 2M parameter model reconstructs transmission map and recovers the clear scene.

04

Crystal Output

Dehazed image in under 50ms. Edge-deployable on NVIDIA Jetson Nano and equivalents.

Live Demo

Drop a foggy image.
Watch it clear.

Paste your deployed Space URL here. This hosted page will call your model API from the web host.

Drag & Drop a Foggy Image

JPG, PNG, WEBP — or click to browse

Processing with NoFogNet…

Dehazed
Foggy
Foggy Clear

Drag the slider to compare

Performance

Numbers that matter

0
Training Images
Largest supervised fog dataset
0
Downloads
GitHub & HuggingFace
0
Parameters
Ultra-lightweight model
0
Latency
Edge AI ready
Fog Science

Six types of fog.
One solution.

Most Common

Radiation Fog

Forms on clear nights as ground cools. Common in valleys, reduces visibility to near zero by dawn.

Coastal

Advection Fog

Warm moist air over cold surfaces. Persistent along coastal highways.

Mountain

Upslope Fog

Moist air forced up terrain. Challenging for autonomous vehicles on mountain passes.

Water

Evaporation Fog

Steam from warm water into cold air. Patchy and unpredictable — hardest to model.

Winter

Freezing Fog

Droplets freeze on contact, coating lenses and sensors. NoFogNet handles the distortion.

Arctic

Ice Fog

Below -30°C water sublimates into ice crystals. Rare but catastrophic for visibility.

Why It Matters

Safer roads.
Cleaner mobility.

Safer Roads

Fog-related crashes cost hundreds of lives yearly. Real-time dehazing gives autonomous vehicles clarity beyond human vision.

Cleaner Mobility

Confident navigation in fog reduces idling and unnecessary detours, cutting emissions across fleets.

Edge AI

2M parameters runs on NVIDIA Jetson Nano. No cloud dependency — fully on-device inference.

Sustainable Computing

Training consumed 92% less compute than transformer-based alternatives. Small model, large impact.

The Team

Built by researchers,
for the real world.

AW

Awais

AD

Adnan

AY

Ayesha

MM

Memoona