NVIDIA nvImageCodec

The nvImageCodec is a library of accelerated codecs with unified interface. It is designed as a framework for extension modules which delivers codec plugins.

This nvImageCodec release includes the following key features:

• Unified API for decoding and encoding images

• Batch processing, with variable shape and heterogeneous formats images

• Codec prioritization with automatic fallback

• Builtin parsers for image format detection: JPEG, JPEG 2000, TIFF, BMP, PNG, PNM, WebP

• Python bindings

• Zero-copy interfaces to CV-CUDA, PyTorch and CuPy

• End-end accelerated sample applications for common image transcoding

Currently there are following native codec extensions:

• nvjpeg_ext

  • Hardware JPEG decoder

  • CUDA JPEG decoder

  • CUDA lossless JPEG decoder

  • CUDA JPEG encoder

• nvjpeg2k_ext

  • CUDA JPEG 2000 decoder (including High Throughput JPEG)

  • CUDA JPEG 2000 encoder

• nvtiff_ext

  • CUDA TIFF decoder

• nvbmp_ext

  • CPU BMP decoder

  • CPU BMP encoder

• nvpnm_ext

  • CPU PNM (PPM, PBM, PGM) encoder

Additionally as a fallback there are following 3rd party codec extensions:

• libjpeg_turbo_ext

  • CPU JPEG decoder

• libtiff_ext

  • CPU TIFF decoder

• opencv_ext

  • CPU JPEG decoder and encoder

  • CPU JPEG 2000 decoder and encoder

  • CPU PNG decoder and encoder

  • CPU BMP decoder and encoder

  • CPU PNM decoder and encoder

  • CPU TIFF decoder and encoder

  • CPU WebP decoder and encoder