vision
DPT (Dense Prediction Transformer)
Intel ViT-based dense prediction model for monocular depth estimation and segmentation; MiDaS v3 is built on it.
Levelmodel
Classvision
Parameters341.85M
Contextnot in the notes
Released24 Mar 2021
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- 341.85M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- image
- Output
- image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperIntelbig tech, USA
Intelbig tech, USAModelDPT (Dense Prediction Transformer)Intel, vision
DPT (Dense Prediction Transformer)Intel, visionR&D TopicsMonocular and Stereo Depth EstimationImage Classification Backbone Architectures (CNN and Vision Transformer)
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
R&D topics 2
Image Classification Backbone Architectures (CNN and Vision Transformer)Designing the core networks that turn an image into features, from residual CNNs to visio…produced byMonocular and Stereo Depth EstimationEstimating the distance of every pixel from one image, a video or a stereo pair.produced by
Sources
- arxiv.org/abs/2103.13413 https://arxiv.org/abs/2103.13413
- huggingface.co/Intel/dpt-large https://huggingface.co/Intel/dpt-large
- ai.azure.com/catalog/models?task=image-segmentation https://ai.azure.com/catalog/models?task=image-segmentation
- paperswithcode.com/method/dense-prediction-transformer https://paperswithcode.com/method/dense-prediction-transformer
- huggingface.co/datasets/pwc-archive/methods https://huggingface.co/datasets/pwc-archive/methods
- arxiv.org/abs/2103.13413v1 https://arxiv.org/abs/2103.13413v1
- github.com/open-mmlab/mmsegmentation/tree/main/configs/dpt https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dpt
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DPT (Dense Prediction Transformer)", https://aurion.semai.id/models/intel-dpt/, records of October 2026.