Video Area Home >> Video Codecs Comparisons >> MSU Video Codecs Comparison 2022

MSU Video Codecs Comparison 2022
Part 1: Hardware encoders

Seventeen Annual Video-Codecs Comparison by MSU

Video group head: Dr. Dmitriy Vatolin Project head: Dr. Dmitriy Kulikov Measurements, analysis: Nikita Alutis, Mikhail Voronin, Nickolay Safonov, Ekaterina Shumitskaya
compression.ru	Lomonosov Moscow State University (MSU) Graphics and Media Lab	Dubna International State University	Institute for Information Transmission Problems, Russian Academy of Science

News

• 15.04.2023 Several typos corrected, leaderboard updated (note: several places changed)
• 14.04.2023 Report release

Navigation

• Description
• Results
• Download report
• Participants
• Rules
• Features
• Thanks
• Contact information

---

Description

---

In MSU Hardware Video Codecs Comparison 2022, we analyzed 14 hardware codecs. There were 3 different speed usecases: 60 fps, 120 fps, 240 fps. 53 FullHD video sequences were used for testing.

Note:

The set of videos used in this comparison consists of less videos than FullHD part because of compatibility issues

---

Results

---

• The places below are given by quality scores
• Encoders with scores closer than ~1% share one place

	Very-fast (60 fps)
Best encoder YUV-SSIM, YUV-PSNR	Streamlake-200 (ASIC), Tencent Canghai 265 (ASIC) BVE (FPGA) BLUEDOT_AV1 (FPGA)
Best encoder Y-VMAF (v0.6.3)	Tencent Canghai 265 (ASIC) BVE (FPGA) Streamlake-200 (ASIC)
Best encoder YUV-VMAF (v0.6.3)	BVE (FPGA), Tencent Canghai 265 (ASIC) Streamlake-200 (ASIC) BLUEDOT_AV1 (FPGA)
Best GPU encoder	Intel QSV AV1 (GPU)
Best FPGA encoder	BVE (FPGA)
Best ASIC encoder	Tencent Canghai 265 (ASIC), Streamlake-200 (ASIC)

	Super-fast (120 fps)
Best encoder YUV-SSIM, Y-VMAF (v0.6.3), YUV-PSNR, YUV-VMAF (v0.6.3)	Tencent Canghai 265 (ASIC) Streamlake-200 (ASIC) Intel QSV AV1 (GPU)
Best GPU encoder	Intel QSV AV1 (GPU)
Best ASIC encoder	Tencent Canghai 265 (ASIC)

	Ultra-fast (240 fps)
Best encoder YUV-SSIM, Y-VMAF (v0.6.3), YUV-PSNR, YUV-VMAF (v0.6.3)	Streamlake-200 (ASIC) Intel QSV AV1 (GPU) NVENC H.265 (GPU)
Best GPU encoder	Intel QSV AV1 (GPU)
Best ASIC encoder	Streamlake-200 (ASIC)

The winners vary for different objective quality metrics. The participants were rated using BSQ-rate (enhanced BD-rate) scores [1].

[1] A. Zvezdakova, D. Kulikov, S. Zvezdakov, D. Vatolin, "BSQ-rate: a new approach for video-codec performance comparison and drawbacks of current solutions," 2020.

Speed/quality trade-off "Very-fast 60 fps" all sequences, YUV (6:1:1)-SSIM metric

Speed/quality trade-off "Very-fast 60 fps (neglecting lookahead i/o time" on three longest sequences, YUV (6:1:1)-SSIM metric

Please note that this year average video length was selected to be bigger to neglect lookahead effect. That is why two charts are very similar

---

Download

---

FPGA Express Report Objective comparison of ultra-fast and hardware-accelerated video encoders Released on April, 14 Full version for free Download ZIP	14 hardware-accelerated encoders Streamlake-200 (ASIC), Tencent Canghai 265 (ASIC), BVE1.1 (FPGA), BLUEDOT_AV1 (FPGA), Reference x265 (CPU), NVENC H.265 (GPU), NVENC H.264 (GPU), Intel QSV AV1 (Intel Arc GPU), Intel QSV H265 (Intel Arc GPU), Intel QSV H264 (Intel Arc GPU), Intel QSV H265 (CPU), Intel QSV H264 (CPU), AMD H.265 (GPU), AMD H.264 (GPU),
	53 FullHD videos 60, 120 and 240 fps usecases
	28+ objective metrics (VMAF, SSIM, MS-SSIM, PSNR of different variants)
	HTML report + links to source videos (ZIP) 5400+ interactive charts

---

Participants

---

	Codec name	Platform	Standard	Usecases	Version
1	Reference x265 MulticoreWare, Inc.	CPU	H.265/HEVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	3.5+1-f0c1022b6, Windows
2	Tencent Canghai 265 Tencent	ASIC	H.265/HEVC	Very-fast, Super-fast (60 fps, 120 fps)	-
3	Streamlake-200 StreamLake-200: Data Center High performance AI-VPU for Cloud, designed for high quality, density, flexibility for cloud and edge. Infrastructure for live streaming, cloud game, broadcasting, embedded Kuaishou leading video technology. Streamlake	ASIC	H.265/HEVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
4	BVE Bytedance	FPGA	-	Very-fast (60 fps)	1.1
5	BLUEDOT_AV1 Pulsar-AV1 FPGA encoder v1.0, 1080p60fps, Available at Azure NP10 Bluedot	FPGA	AV1	Very-fast (60 fps)	1.0
6	NVENC H.265 (NVIDIA Titan RTX GPU)	GPU	H.265/HEVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
7	NVENC H.264 (NVIDIA Titan RTX GPU)	GPU	H.265/HEVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
8	Intel QSV AV1 (Intel Arc GPU) Intel Corp.	GPU	AV1	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
9	Intel QSV H.265 (Intel Arc GPU) Intel Corp.	GPU	H.265/HEVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
10	Intel QSV H.264 (Intel Arc GPU) Intel Corp.	GPU	H.264/AVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
11	Intel QSV H.265 (Intel Core i7 12700K) Intel Corp.	CPU (built-in hardware acceleration)	H.265/HEVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
12	Intel QSV H.264 (Intel Core i7 12700K) Intel Corp.	CPU (built-in hardware acceleration)	H.264/AVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	-
13	AMD H.265 (Radeon RX6800) AMD	GPU	H.265/HEVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	1.4.29, Windows
14	AMD H.264 (Radeon RX6800) AMD	GPU	H.264/AVC	Very-fast, Super-fast, Ultra-fast (60 fps, 120 fps, 240 fps)	1.4.29, Windows

---

Comparison Rules

---

Hardware-accelerated and ultra-fast codecs testing objectives

The main goal of this report is the presentation of a comparative evaluation of the quality of new and existing codecs using objective measures of assessment. The comparison was done using settings provided by the developers of each codec. Nevertheless, we required all presets to satisfy minimum speed requirement on the particular use case. The main task of the comparison is to analyze different encoders for the task of transcoding video – e.g., compressing video for personal use.

Test Hardware Characteristics for GPU/ASIC encoders

• CPU: Intel Core i7 12700K (Alder Lake)
• SSD: 1Tb
• RAM: 4x16GB (64GB)
• OS: Windows 11 x64, Ubuntu 22.04 LTS

Test Hardware Characteristics for FPGA encoders

• CPU: Intel Core i7 12700K (Alder Lake)
• SSD: 1Tb
• FPGA: Xilinx Alveo U250 Accelerator
• RAM: 4x16GB (64GB)
• OS: Windows 11 x64, Ubuntu 22.04 LTS

See more on Call For Codecs 2022 page

Videos

Videos for testing set were chosen from MSU video collection via a voting among comparison participants, organizers and an independend expert.

Number of videos in MSU video collection

Year	# FullHD videos	# FullHD samples	# 4K videos	# 4K samples	Total # of videos	Total # of samples
2016	3	7	882	2902	885	2909
2017	1996	4638	1544	4561	3540	9299
2018	4342	10330	1946	5503	6288	15833
2020	4945	12402	2091	6016	7036	18418
2021	4945	12402	2091	6016	7036	18418
2022	7379	19546	2091	6016	9470	25562

Bitrate distribution of videos in MSU video collection

Final video set consists of 53 sequences including new videos from Vimeo and media.xiph.org derf's collection.

Descriptions of all test videos are presented in a separate PDF provided with the report.

---

Codec Analysis and Tuning for Codec Developers and Codec Users

---

Computer Graphics and Multimedia Laboratory of Moscow State University:

• 17+ years working in the area of video codec analysis and tuning using objective quality metrics and subjective comparisons.
• 30+ reports of video codec comparisons and analysis (H.265, H.264, AV1, VP9, MPEG-4, MPEG-2, decoders' error recovery).
• Methods and algorithms for codec comparison and analysis development, separate codec's features and codec's options analysis.

Strong and Weak Points of Your Codec

• Deep encoder parts analysis (ME, RC on GOP, mode decision, etc).
• Weak and strong points for your encoder and complete information about encoding quality on different content types.
• Encoding Quality improvement by the pre and post filtering (including technologies licensing).

Independent Codec Estimation Comparing to Other Codecs for Different Use-cases

• Comparative analysis of your encoder and other encoders.
• We have direct contact with many codec developers.
• You will know place of your encoder between other newest well-known encoders (compare encoding quality, speed, bitrate handling, etc.).

Encoder Features Implementation Optimality Analysis

We perform encoder features effectiveness (speed/quality trade-off) analysis that could lead up to 30% increase in the speed/quality characteristics of your codec. We can help you to tune your codec and find best encoding parameters.

---

Thanks

---

Special thanks to the following contributors of our previous comparisons

---

Contact Information

---

Subscribe to report updates

---

---

---

Other Materials

---

Video resources:

3D and stereo video Projects on 3D and stereo video processing and analysis MSU S3D-video analysis reports MSU 3D Devices Testing 3D Displays Video Generation 3D Displays Video Capturing Stereo Video Depth Map Generation SAVAM Saliensy-Aware Video Compression & Dataset Video Matting Benchmark Video Inpainting Benchmark MSU Video Quality Measurement tools Programs with different objective and subjective video quality metrics implementation MSU Video Quality Measurement Tool - objective metrics for codecs and filters comparison Implemented metrics short info: PSNR, Delta, MSAD, MSE, SSIM, VQM, MSU Blurring Metric, MSU Blocking Metric Why update Download & Purchase Documentation MSU Human Perceptual Quality Metric - several metrics for exact visual tests Methods info: ITU-R BT.500-11: DSIS, DSCQS I & II, SCACJ; EBU: SAMVIQ; MSUCQE; Custom Download Documentation	Codecs comparisons Objective and subjective quality evaluation tests for video and image codecs MSU Video Codecs Comparison 2023-2024 MSU Video Codecs Comparison 2022 MSU Video Codecs Comparison 2021 MSU Video Codecs Comparison 2020 MSU Cloud Benchmark 2020 Cloud Encoding Services Comparison 2019 HEVC/AV1 Codec Comparison 2019 HEVC/AV1 Codec Comparison 2018 HEVC/AV1 Codec Comparison 2017 HEVC Codec Comparison 2016 HEVC Codec Comparison 2015 9-th MPEG4-AVC/H.264 Comparison 8-th MPEG4-AVC/H.264 Comparison 7-th MPEG4-AVC/H.264 Comparison 6-th MPEG4-AVC/H.264 Comparison 5-th MPEG4-AVC/H.264 Comparison Codec Analysis for Companies: Private Video Codec Comparison MSU Video Quality Measurement Tool Options Analysis of Codec x264 4-th MPEG4-AVC/H.264 Comparison Lossless Video Codecs Comparison 2007 3-rd MPEG4-AVC/H.264 Comparison HD Photo and JPEG 2000 Comparison MPEG-2 Decoders Crash Test Subjective Compar. of 4 Modern Codecs 2-nd MPEG-4 AVC/H.264 Comparison FAQ of 2-nd H.264 Comparison 1-st MPEG-4 AVC/H.264 Codecs Comparison FAQ of 1-st H.264 Comparison JPEG 2000 Image Codecs Comparison Lossless Video Codecs Comparison 2004 MPEG-4 SP/ASP Codecs Comparison Video codecs comparison (old) Ext. link: x264 parameters efficiency comparison
Public MSU video filters Here are available VirtualDub and AviSynth filters. For a given type of digital video filtration we typically develop a family of different algorithms and implementations. Generally there are also versions optimized for PC and hardware implementations (ASIC/FPGA/DSP). These optimized versions can be licensed to companies. Please contact us for details via video(at)graphics.cs.msu_ru. MSU Cartoon Restore MSU Noise Estimation MSU Frame Rate Conversion MSU Image Restoration MSU Denoising MSU Old Cinema MSU Deblocking MSU Smart Brightness and Contrast MSU Smart Sharpen MSU Noise generation MSU Noise estimation MSU Motion Estimation Information MSU Subtitles removal MSU Logo removal MSU Deflicker MSU Field Shift Fixer AviSynth plug-in MSU StegoVideo MSU Cartoonizer MSU SmartDeblocking MSU Color Enhancement MSU Old Color Restoration MSU TV Commercial Detector MSU filters FAQ MSU filters statistics	Filters for companies We are working with Intel, Samsung, RealNetworks and other companies on adapting our filters other video processing algorithms for specific video streams, applications and hardware like TV-sets, graphics cards, etc. Some of such projects are non-exclusive. Also we have internal researches. Please let us know via video(at)graphics.cs.msu_ru if you are interested in acquiring a license for such filters or making a custom R&D project on video processing, compression, computer vision. 3D Displays Video Generation 3D Displays Video Capturing Stereo Video Depth Map Generation Automatic Objects Segmentation Semiautomatic Objects Segmentation New Frame Rate Conversion New Deinterlacer MSU-Samsung Deinterlacing Project Digital TV Signal Enhancement Old Film Recovery Tuner TV Restore Panorama Video2Photo SuperResolution SuperPrecision MSU-Samsung image and video resampling MSU-Samsung Frame Rate Conversion Motion Phase filter Deshaker (video stabilization) Film Grain/Degrain filter Deblurring filter Video Content Search
Video codecs projects Different research and development projects on video codecs MSU Lossless Video Codec (Top!) MSU Screen Capture Lossless Codec (Top!) MSU MPEG-2 Video Codec x264 Codec Improvement	Other Other information Crazy gallery (filters screams :) License for commercial usage of MSU VideoGroup Public Software (please be careful: some soft like metrics has another license!)

Last updated: 12-May-2022

---

Server size: 8069 files, 1215Mb (Server statistics)

Project updated by
Server Team and MSU Video Group

Project sponsored by YUVsoft Corp.

Project supported by MSU Graphics & Media Lab