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
DLPP
Model
NVIDIA
NVIDIA
DLPP

DLPP is a family of lightweight deep-learning networks trained for video post-processing. The model's introduction can be found at https://blogs.nvidia.com/blog/rtx-video-super-resolution/. To the public, it is also known as RTX VSR.

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:Super Resolution and Image Restoration.
Model Type:CNN.
Intended Users:End-users of our GPUs.
Output:Red, Green, Blue (RGB) images.
Describe how the model works:The model takes RGB images and improves their visual quality by removing compression artifacts and increasing resolution.
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:Not Applicable
Technical Limitations & Mitigation:Real-world videos often suffer from multiple types of degradation, such as blur, noise, and compression artifacts. Our model is trained on limited types of degradation, it may struggle to address all these issues simultaneously.
Verified to have met prescribed NVIDIA quality standards:Yes
Performance Metrics:Mean Opinion Score.
Potential Known Risks:This model may create unwanted patterns in the output video when the input video is heavily distorted.
Licensing:http://nvidia.com/en-us/drivers/geforce-license/