vision
PGD (Probabilistic and Geometric Depth)
Monocular 3D detector with probabilistic and geometric depth estimation.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released29 Jul 2021
Opennessunknown
Runs onnot in the notes
Statusactive
Identity
- Developer
- The Chinese University of Hong Kong
- Family
- not in the notes
- Released
- 29 Jul 2021 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
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
- CNN
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- Checkpoints in OpenMMLab MMDetection3D; repository licence Apache-2.0, weight terms not separately stated.
- Context length
- not in the notes
- Input
- image
- Output
- 3D
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
- unknown
- Licence
- not in the notes sources
- Access routes
- open weights download
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
ModelPGD (Probabilistic and Geometric Depth)The Chinese University of Hong Kong, vision
PGD (Probabilistic and Geometric Depth)The Chinese University of Hong Kong, visionR&D TopicsLiDAR and Multi-Sensor 3D Perception
Use Casesnone recorded
Who Runs Itnone recorded
Sources
- arxiv.org/abs/2107.14160 https://arxiv.org/abs/2107.14160
- github.com/open-mmlab/mmdetection3d/tree/main/configs/pgd https://github.com/open-mmlab/mmdetection3d/tree/main/configs/pgd
- arxiv.org/html/2107.14160 https://arxiv.org/html/2107.14160
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "PGD (Probabilistic and Geometric Depth)", https://aurion.semai.id/models/pgd-mono3d/, records of October 2026.