Documentation Index
Fetch the complete documentation index at: https://imcui.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Configuration
Image Matching WebUI uses YAML configuration files to customize behavior and default parameters.Configuration File Location
Configuration files are loaded in priority order (first found):- Custom path:
-c /path/to/config.yaml - Working directory:
./app.yaml - Config subdirectory:
./config/app.yaml - Package default:
imcui/config/app.yaml
Essential Settings
Device Selection
Device is automatically detected at runtime based on your hardware:- CUDA: Auto-selected if CUDA GPU is available
- CPU: Default fallback when CUDA is unavailable
- MPS: Auto-selected on macOS with Apple Silicon
Force CPU Mode
Force CPU Mode
Set environment variable before running:
Select Specific GPU
Select Specific GPU
Use environment variable:
Default Matcher
There is nodefault_matcher configuration. Matchers are loaded dynamically from the vismatch package and selected through the UI dropdown during matching.
Available matchers: See algorithm reference
Matching Parameters
Thresholds
RANSAC Filtering
RANSAC- Basic random samplingCV2_USAC_MAGSAC- Magnitude-consistent RANSAC (recommended)LMEDS- Least Median of Squares
Geometry Estimation
Essential Matrix Settings
Essential Matrix Settings
Note: Essential matrix parameters are configured through the UI when selecting Essential matrix geometry type.
Requires camera intrinsics (focal length and principal point).
Example Configurations
Minimal Setup
Production Configuration
Development Configuration
Developer note: Set
CUDA_VISIBLE_DEVICES="" before running to force CPU mode.Advanced Configuration
Dataset Path
Tip: Dataset paths can also be set via environment variable (
IMCUI_DATA_DIR) or CLI flag (-d).Configuration Profiles
Create multiple configurations for different use cases:Using Matchers
Matchers are selected through the web interface dropdown. The available matchers are automatically loaded from the vismatch package:- Sparse matchers: SuperPoint + LightGlue, ORB, SIFT, etc.
- Dense matchers: LoFTR, RoMa, etc.
Need help selecting a matcher? Check our algorithm guide for performance characteristics and recommendations.