Project AURIONAI Use-Cases Research & Innovation
University of Texas at Austin
vision

H3DNet

Indoor 3D object detection using hybrid geometric primitives.

University of Texas at AustinUniversity of Texas at AustinUSA
Figure from the H3DNet paper: Our approach leverages a hybrid and overcomplete set of geometric primitives to detect and refine 3D object bounding boxes (BBs).
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released10 Jun 2020
Opennessunknown
Runs onnot in the notes
Statusactive

R&D Topics

LiDAR and multi-sensor 3D perceptionproduced by

Identity

Developer
University of Texas at Austin
Family
not in the notes
Released
10 Jun 2020 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
3D
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.

Sources

  1. arxiv.org/abs/2006.05682 https://arxiv.org/abs/2006.05682
  2. github.com/open-mmlab/mmdetection3d/tree/main/configs/h3... https://github.com/open-mmlab/mmdetection3d/tree/main/configs/h3dnet
  3. arxiv.org/html/2006.05682 https://arxiv.org/html/2006.05682

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "H3DNet", https://aurion.semai.id/models/h3dnet/, records of October 2026.