NVIDIA
NVIDIA
Bi3D Proximity Segmentation
Model
NVIDIA
NVIDIA
Bi3D Proximity Segmentation

Bi3D is a binary depth classification network that is used to classify the depth of objects at a given distance.

3 Versions
10/13/2022 8:22 PM UTC62.98 MBAccuracy: 97900 EpochsBatch Size: 80GPU: V100
MODEL OVERVIEW
KeyValue
BackboneResnet18Unet
ImprovementSegmentation of Textureless Regions
DescriptionBinary Proximity Segmentator
OutputProximity Segmentation Maps
VERSION2.0.0
TrainableFalse
Supported OSLINUX, LINUX4TEGRA
1.1.0Selected
08/30/2022 5:25 PM UTC63.12 MBAccuracy: 97600 EpochsBatch Size: 96GPU: V100
MODEL OVERVIEW
KeyValue
BackboneResnet18Unet
DescriptionBinary Proximity Segmentator
OutputProximity Segmentation Maps
VERSION1.1.0
TrainableFalse
Supported OSLINUX, LINUX4TEGRA
06/28/2022 10:31 PM UTC62.46 MBAccuracy: 97500 EpochsBatch Size: 96GPU: V100

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.