|
Fastvideo Freeware and Demo Downloads
You can find below links for our demo and freeware software for image processing applications. This software is prepared for non-commercial use only. It is free for personal and educational use (including non-profit organizations). Distribution of this software without any permission from Fastvideo is NOT allowed. NO warranty and responsibility is provided by the authors for the consequences of using it. That software is based on Fastvideo Image & Video Processing SDK and here you can download the document with Fastvideo SDK benchmarks.
Installation
Unzip all files into working folder and run console application from command line with parameters specified in Readme.txt. It's necessary to have NVIDIA GPU (Maxwell, Pascal, Volta, Turing, Ampere) installed to run the software on GPU. For the latest NVIDIA drivers visit NVIDIA Drivers Downloads. To get better performance use images with high resolution. If you need Linux version, please send us your request via contact form.
Software and Hardware Requirements
- OS Windows-10 (64-bit)
- Demo downloads for OS Linux Ubuntu/CentOS and L4T are available upon request
- NVIDIA GPU with Compute Capability >= 3.0
- Optimized for NVIDIA GPUs with Pascal, Volta, Turing, Ampere, Ada architectures
- Available for NVIDIA Jetson TX2, NX and AGX Xavier, NX and AGX Orin
- Download Fastvideo SDK manual
Fast JPEG Codec on CUDA
|
- Implementation is 100% compliant with JPEG Baseline standard
- JPEG encoding and decoding for grayscale 8-bit and color 24-bit images (Baseline part of JPEG Standard)
- JPEG encoding and decoding for 12-bit grayscale and 36-bit color images (Extension to JPEG Standard)
- Supported image formats: BMP, PPM, PGM, JPG
- Data input: 8/24-bit or 12/36-bit images from HDD/RAID/SSD
- Data output: final compressed/uncompressed images at HDD/RAID/SSD
- JPEG image quality in the range from 1 to 100%
- Subsampling modes 4:4:4, 4:2:2, 4:2:0
- Performance measurements option
|

|
Fast JPEG Codec on CUDA
Size: 55.0 MB
Publisher: Fastvideo
OS: Windows-10 (64-bit)
License: Freeware
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada
|
Fast JPEG2000 Codec on GPU |
- JPEG2000 encoding and decoding for grayscale 8/16-bit and color 24/48-bit images
- Supported image formats: BMP, PPM, PGM, J2K, JP2
- Data input: 8/10/12/14/16-bit monochrome or color images from HDD/RAID/SSD
- Data output: final compressed images at HDD/RAID/SSD
- Lossy JPEG2000 compression and decompression with CDF 9/7 wavelet
- Lossless JPEG2000 compression and decompression with CDF 5/3 wavelet
- Subsampling modes 4:2:0, 4:2:2, 4:4:4
- Number of DWT levels up to 12
- Codeblock size: 16×16, 32×32, 64×64
- JPEG2000 image quality in the range from 1 to 100 (float value)
- Quality layers – one
- Progression order – LRCP (L = layer, R = resolution, C = component, P = position)
- Modes of operation – single, batch, multithreaded-batch
- Performance measurements option
|

|
Fast JPEG2000 GPU Codec
Size: 39.2 MB
Publisher: Fastvideo
OS: Windows-10 (64-bit)
License: Freeware
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada |

|
Fast J2K Viewer on GPU
Size: 51 MB
Publisher: Fastvideo
OS: Windows-10 (64-bit)
License: Time-limited demo
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada |
Fast MXF Player on GPU |
- MXF (JPEG2000) decoding in realtime
- Data input: 8/10/12/14/16-bit images/video from HDD/RAID/SSD
- Lossless/lossy JPEG2000 decoding with CDF 5/3 and 9/7 wavelets
- Subsampling modes 4:2:0, 4:2:2, 4:4:4
- Number of DWT levels up to 7
- Codeblock size: 16×16, 32×32, 64×64
- Quality layer – one
- Progression order – LRCP (L = layer, R = resolution, C = component, P = position)
- Performance measurements option
- Two-GPU option (one GPU to decode MXF, the other to display on the monitor)
|

|
Fast MXF Player on GPU
Size: 99.8 MB
Publisher: Fastvideo
OS: Windows-10 (64-bit)
License: Time-limited demo
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada |
Fast Debayer on CUDA
|
- All Bayer mosaic patterns for input data supported (RGGB, BGGR, GBRG, GRBG)
- Mosaic algorithm to prepare CFA input image from any 24/48-bit PPM image
- Read 8/16-bit input CFA image data from HDD/SSD/RAID in PGM format
- Output format: 24/48-bit PPM
- GPU Debayer algorithms: HQLI, L7, DFPD, MG
- Strong color moire artifacts suppression
- Performance measurements option for each algorithm
|

|
Fast Debayer on CUDA
Size: 59.1 MB
Publisher: Fastvideo
OS: Windows-10 (64-bit)
License: Freeware
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada
|
Fast CinemaDNG Processor on CUDA
|
- GPU raw processing for CinemaDNG, MLV, BRAW
- Raw Tone Curves before debayering
- High quality demosaicing with MG algorithm
- High speed denoising for raw, luma and chroma
- No proxies, 4K/6K dailies can be processed in realtime
- Smooth and scalable Player for CinemaDNG sequences and MLV video
- Trimming, Culling and Reviewing footage before editing
- Support of Blackmagic CinemaDNG RAW 3:1 and 4:1 formats
- Other RAW formats: CR2, CR3, NEF, ARW, IIQ, etc.
- Recompression and cutting of RAW footage
- Magic Lantern MLV player, viewer and converter
- DCP support: 3D HSV and LookTable, Tone Curve
- LCP support for lens profiles
- 3D LUT support (RGB)
- Realtime benchmarking
- Output: JPEG, TIFF, J2K, ProRes (MOV), MJPEG (AVI)
- Download CinemaDNG footages for testing
|

|
Fast CinemaDNG Processor on GPU
Size: 141 MB (Windows)
Publisher: Fastvideo
OS: Windows-10 (64-bit), Ubuntu 18.04, 19.10, 20.04
License #1: Standard, ver. 1.0.16
License #2: PRO Server - available by request
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada
|
FastVCR software for machine vision cameras
|
- Camera initialization (camera model, resolution, fps, etc.)
- Camera control: input bit depth, image resolution and ROI, FPS and exposure time, Gain, camera bandwidth test
- Optional modes: binning, decimation, dual gain, dual adc, etc.
- Camera statistics: real fps, dropped frames, etc.
- Image acquisition
- Bad pixel removal
- White Balance / AWB
- Adaptive Exposure and Gain control in real time
- High quality demosaicing with MG algorithm
- Color Correction with matrix profile or DCP profile
- Highlight recovery
- Exposure correction (brightness control)
- Wavelet-based denoising
- Rotation (90/180/270 degrees) and flip/flop
- Resize (downscale and upscale)
- Sharpening
- Gamma transform
- JPEG/MJPEG compression and storage to SSD
- H264/H265/AV1 GPU-based encoding, streaming via RTSP, storage to SSD
- Realtime output to monitor
- CLI application (optional)
- Multicamera support (optional)
|

|
FastVCR software for XIMEA cameras
Size: 83.9 MB (Windows)
Publisher: Fastvideo
OS: Windows-10 (64-bit), Ubuntu 18.04, 19.10, 20.04, L4T
License #1: Demo
NVIDIA GPU: Jetson TX2, NX/AGX Xavier, Orin
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada
|
Fastvideo SDK for image processing on CUDA
|
- Image ingestion from a camera, frame grabber, HDD/SSD/RAM or GPU memory (PGM, BMP, PPM, JPG, YCbCr, RAW, DNG, byte array, OpenGL texture or PBO, etc.)
- Raw data unpacking on GPU
- Raw data linearization
- Dark frame subtraction (FPN)
- Flat-Field Correction (Shading Correction)
- White Balance
- Bad pixel suppression
- Exposure correction
- Raw Bayer Curves (master and RGB)
- Raw Denoising with wavelets and with median filter
- Demosaicing with HQLI, L7, DFPD, MG algorithms
- Denoising for luma and chroma
- Color Correction with matrix profile
- Color Transforms: RGB->YCbCr, YCbCr->RGB, RGB->HSV, HSV->RGB, etc.
- Composite or per-color component 8/10/12/14/16-bit 1D LUTs for tone mapping in RGB or HSV (Hue->Hue, Hue->Saturation, etc.)
- 3D LUT for RGB and HSV
- RGB Histograms
- Crop
- Rotate to 90/180/270 degrees and flip/flop
- Resize (downscale or upscale)
- Remap (rotation to arbitrary angle, affine transform, perspective transform, projection, arbitrary mapping)
- Gamma transform (composite or per-color component)
- Sharpening with Unsharp Mask filter (USM)
- Realtime output via OpenGL
- JPEG codec (8/12 bits per channel)
- Raw Bayer codec for lossy compression or decompression (8/12 bits per channel)
- H.264 / H.265 encoding and decoding on GPU
- Trace
- Multiplexor
- Stream-per-thread support for better performance
- NVML support: GPU utilization, temperature, fan speed, power management
- NVIDIA Jetson TX2, NX and AGX Xavier, AGX Orin support
- FFmpeg filters and codecs on GPU (Remap, J2K, SDI in/out, etc.)
|
|
Fastvideo SDK for GPU Image Processing
Size: 117 MB (Windows)
Publisher: Fastvideo
OS: Windows-10 (64-bit), Linux, L4T
License: Demo, ver. 0.18.2.0
NVIDIA GPU: Pascal, Volta, Turing, Ampere, Ada and Jetson TX2, NX/AGX Xavier, AGX Orin
|
Open source projects from Fastvideo
|