# 使用超分辨率对图像进行放大

在为某个模型运行 pipeline 命令之前，请遵循所需的[先决条件](https://docs.qualcomm.com/doc/80-70020-15BY/topic/ai-hub-qualcomm-im-sdk.html#prerequisites)

Note

输入尺寸为 128x128 的视频，以获得最佳效果。

运行以下命令以确保您的结果显示在连接的显示器上。

export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1
    Copy to clipboard

## QuickSRNetLarge

QuickSRNetLarge 旨在在移动平台上放大图像以实时锐化它们。

AI Hub 模型基于 [QuickSRNetLarge](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet) 的实现。

- 模型：[QuickSRNetLarge](https://aihub.qualcomm.com/iot/models/quicksrnetlarge)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_0::position="<0, 0>" sink_0::dimensions="<960, 1080>" sink_1::position="<960, 0>" sink_1::dimensions="<960, 1080>" ! \
    queue ! waylandsink sync=true fullscreen=true \
    split. ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/quicksrnetlarge_quantized.tflite ! queue ! \
    qtimlvsuperresolution module=srnet constants="qsrnetlarge,q-offsets=<0.0>,q-scales=<1.0>;" ! video/x-raw,format=RGB ! queue ! mixer.
    Copy to clipboard

## QuickSRNetMedium

QuickSRNetMedium 旨在在移动平台上放大图像以实时锐化它们。

AI Hub 模型基于 [QuickSRNetMedium](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet) 的实现。

- 模型：[QuickSRNetMedium](https://aihub.qualcomm.com/iot/models/quicksrnetmedium)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_0::position="<0, 0>" sink_0::dimensions="<960, 1080>" sink_1::position="<960, 0>" sink_1::dimensions="<960, 1080>" ! \
    queue ! waylandsink sync=true fullscreen=true \
    split. ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/quicksrnetmedium_quantized.tflite ! queue ! \
    qtimlvsuperresolution module=srnet constants="qsrnetlarge,q-offsets=<0.0>,q-scales=<1.0>;" ! video/x-raw,format=RGB ! queue ! mixer.
    Copy to clipboard

## QuickSRNetSmall

QuickSRNetSmall 旨在在移动平台上放大图像以实时锐化它们。

AI Hub 模型基于 [QuickSRNetSmall](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet) 的实现。

- 模型：[QuickSRNetSmall](https://aihub.qualcomm.com/iot/models/quicksrnetsmall)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_0::position="<0, 0>" sink_0::dimensions="<960, 1080>" sink_1::position="<960, 0>" sink_1::dimensions="<960, 1080>" ! \
    queue ! waylandsink sync=true fullscreen=true \
    split. ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/quicksrnetsmall_quantized.tflite ! queue ! \
    qtimlvsuperresolution module=srnet constants="qsrnetlarge,q-offsets=<0.0>,q-scales=<1.0>;" ! video/x-raw,format=RGB ! queue ! mixer.
    Copy to clipboard

## XLSR

XLSR 旨在轻量级实时放大图像。

AI Hub 模型基于 [XLSR](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/xlsr) 的实现。

- 模型：[XLSR](https://aihub.qualcomm.com/iot/models/xlsr)

gst-launch-1.0 -e --gst-debug=2 \
    filesrc location=/etc/media/video.mp4 ! qtdemux ! queue ! h264parse ! v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! tee name=split \
    split. ! queue ! qtivcomposer name=mixer sink_0::position="<0, 0>" sink_0::dimensions="<960, 1080>" sink_1::position="<960, 0>" sink_1::dimensions="<960, 1080>" ! \
    queue ! waylandsink sync=true fullscreen=true \
    split. ! qtimlvconverter ! queue ! qtimltflite delegate=external external-delegate-path=libQnnTFLiteDelegate.so \
    external-delegate-options="QNNExternalDelegate,backend_type=htp;" model=/etc/models/xlsr_quantized.tflite ! queue ! \
    qtimlvsuperresolution module=srnet constants="qsrnetlarge,q-offsets=<0.0>,q-scales=<1.0>;" ! video/x-raw,format=RGB ! queue ! mixer.
    Copy to clipboard

Last Published: Oct 12, 2025

[Previous Topic
对视频帧应用语义分割](https://docs.qualcomm.com/bundle/publicresource/80-70020-15BY/topics/semantic-segmentation.md) [Next Topic
故障排除和常见问题解答](https://docs.qualcomm.com/bundle/publicresource/80-70020-15BY/topics/troubleshooting.md)