ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
NvDepthAnythingV2
Model
NVIDIA
NVIDIA
NvDepthAnythingV2

monocular relative depth estimation model.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Task/Domain:Monocular Depth Estimation
Model Type:Transformer
Intended Users:This model is intended for developers working in industrial, robotics, and smart space applications
Output:Depth Map
Describe how the model works:Image input is encoded into features, then depth map is estimated using Dense Prediction Transformers(DPT) Head
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:Not Applicable
Technical Limitations & Mitigation:The model may fail to estimate very sharp edges (for example, where pixel values change quickly) in complex scenes.
Verified to have met prescribed NVIDIA quality standards:Yes
Performance Metrics:Accuracy - delta-1 (D1)
Potential Known Risks:The model may fail to estimate fine grain details in complex scenes (for example, scenes with complex textures).
Licensing:NVIDIA Open Model License Additional Information: Apache 2.0