BlenderProc
DLR
Training image models needs labelled pictures, and collecting enough of them in the field is slow. This is a code pipeline that builds rendered scenes with labels already attached, using open source three dimensional graphics software.
QUICK INFO
SOLUTION TYPE
Models, data & tools
TECHNOLOGY CATEGORY
Simulation, digital twins & world models
AREA OF WORK
Agrifood data & AI infrastructure
ACCESS
Free
DEPLOYMENT
Self-hosted / on-premise · Downloadable
SOURCE REVIEWED
August 17, 2026
What it helps with
- Make labelled training images without field work
- Generate practice crop photos for vision models
- Get more images to train a detector
- Build 3d scenes with labels already attached
- Avoid hand labelling thousands of photos
- Synthetic images for crop protection models
Scope & audience
WHO IT'S FOR
Developer / AI builder · Scientist / researcher
AREA OF WORK
Agrifood data & AI infrastructure
COMMODITY / SCOPE
Crop protection
Access & technical details
ACCESS
Anyone can get it
INTERFACE
Code repository
DEPLOYMENT
You run it yourself
LANGUAGES
Not stated by provider
Featured media
Source information
This listing was compiled from publicly available source material. Verify current details with the provider.
PROVIDER DOCUMENTATION
Reviewed August 2026
Explore more like this
WeedGeneration
University of Tokyo Field Phenomics Lab
Models, data & tools
You need many more weed photos than your field trials produced before a recognition model has enough to learn from. This is a generator with downloadable weights and notebooks that produces artificial weed images on your machine or in the cloud.
Free
Self-hosted / on-premise · Downloadable
Simulation, digital twins & world models
WeedGeneration
diagnose-protect-assure
crop-protection-and-plant-health
buildable-or-downloadable-component
simulation-digital-twins-and-world-models
Free
Self-hosted / on-premise · Downloadable
August 17, 2026
- What weed is growing in my field
- Make more weed photos for training
- Train a weed recognition model with few photos
- My field trials did not produce enough images
- Generate artificial weed pictures on my machine
- Downloadable weights for weed image generation
SDG4AD
Smart-Agri-DIAG
Models, data & tools
Damaged or odd looking bunches are rare in your photo archive, so a defect spotter has little to learn from. This is a code pipeline that creates artificial images of flawed table grapes to pad out training sets.
Free · Open source
Self-hosted / on-premise · Downloadable
Simulation, digital twins & world models
SDG4AD
diagnose-protect-assure
crop-protection-and-plant-health
buildable-or-downloadable-component
simulation-digital-twins-and-world-models
Free · Open source
Self-hosted / on-premise · Downloadable
August 17, 2026
- Spot damaged table grapes on a line
- Train a defect spotter with few examples
- Make artificial images of flawed grapes
- Pad out a small grape image set
- Find odd looking grape bunches automatically
- Generate rare defect pictures for training
Is this your Resource?
Contact us to claim this listing and add details, screenshots or a demo.