Author

Kuaishou Audio & Video Technology

Explore the stories behind Kuaishou's audio and video technology.

Articles

Likes

109

Views

Comments

Latest from Kuaishou Audio & Video Technology

25 recent articles

Kuaishou Audio & Video Technology

Jun 9, 2026 · Artificial Intelligence

CVPR NTIRE 2026 UGC Short‑Video Restoration Challenge: Winning Solutions and Highlights

The CVPR NTIRE 2026 challenge introduced the KwaiVIR benchmark for real‑world UGC short‑video degradation, attracted 95 registered teams with 12 final submissions from 14 universities and 5 companies, evaluated on subjective human scores and objective metrics (PSNR, SSIM, LPIPS, MUSIQ, WarpError), and saw RedMediaTech achieve the top overall performance with a subjective score of 3.8525 and the best objective results (PSNR 30.7610, SSIM 0.8504, LPIPS 0.1910), while detailed analyses of the leading three methods reveal diverse two‑stage diffusion and generative pipelines.

CVPRDeep LearningNTIRE

0 likes · 10 min read

CVPR NTIRE 2026 UGC Short‑Video Restoration Challenge: Winning Solutions and Highlights

Kuaishou Audio & Video Technology

Sep 4, 2025 · Fundamentals

How LingXi Revolutionizes User‑Level QoE with Scalable Adaptive Video Streaming

A joint Kuaishou‑Tsinghua study presented at ACM SIGCOMM 2025 introduces LingXi, the first large‑scale production system that personalizes adaptive video streaming by targeting stall events, using online Bayesian optimization, Monte Carlo simulation, and a hybrid exit‑rate predictor to achieve significant QoE and QoS gains across millions of users.

Monte Carlo simulationQoE optimizationSIGCOMM 2025

0 likes · 14 min read

How LingXi Revolutionizes User‑Level QoE with Scalable Adaptive Video Streaming

Kuaishou Audio & Video Technology

Jun 11, 2025 · Artificial Intelligence

Kuaishou Showcases 12 Cutting-Edge CVPR 2025 Papers on Video Generation and AI

Kuaishou presented twelve peer‑reviewed papers at CVPR 2025 covering video quality assessment, large‑scale video datasets, dynamic 3D avatar reconstruction, 4D scene simulation, controllable video generation, scaling laws for diffusion transformers, multimodal foundations, and more, highlighting the company's leading research in computer vision and AI.

AI researchCVPR2025Deep Learning

0 likes · 21 min read

Kuaishou Showcases 12 Cutting-Edge CVPR 2025 Papers on Video Generation and AI

Kuaishou Audio & Video Technology

Jan 21, 2025 · Fundamentals

How Kuaishou Enables Full‑Chain Dolby Vision Support for UGC

Kuaishou partners with Dolby Labs to bring full‑chain Dolby Vision to its short‑video platform, detailing the technology behind HDR, dynamic metadata, and a brightness‑adjustment solution that ensures seamless playback and optimal visual experience for user‑generated content across devices.

Dolby VisionDynamic MetadataExtended Brightness

0 likes · 10 min read

How Kuaishou Enables Full‑Chain Dolby Vision Support for UGC

Kuaishou Audio & Video Technology

Jun 20, 2023 · Artificial Intelligence

How a Low‑Latency Hierarchical Fusion Network Beats Echoes in Real‑Time Calls

At ICASSP 2023, Kuaishou’s audio team presented a low‑latency hierarchical fusion network for full‑band acoustic echo cancellation, detailing its multi‑stage design, asymmetric windowing, loss functions, training strategy, and achieving second place in the non‑personalized AEC Challenge, with real‑world deployment results.

Acoustic Echo CancellationDeep LearningHierarchical Fusion Network

0 likes · 13 min read

How a Low‑Latency Hierarchical Fusion Network Beats Echoes in Real‑Time Calls

Kuaishou Audio & Video Technology

May 25, 2023 · Fundamentals

What Makes Kuaishou’s CMTP the Future of Media Transmission?

The article reviews the rapid growth of audio‑video applications, categorizes media transmission scenarios into generic VoD, RTC and Live, examines Kuaishou’s optimization practices with protocols such as KTP, LAS, KLP and AAS, and introduces the next‑generation CMTP protocol designed to unify and extend these solutions across all use cases.

CMTPKTPaudio-video streaming

0 likes · 12 min read

What Makes Kuaishou’s CMTP the Future of Media Transmission?

Kuaishou Audio & Video Technology

Mar 30, 2023 · Artificial Intelligence

How Kuaishou Elevates Short‑Video Quality and AI Performance at NVIDIA GTC 2023

At NVIDIA GTC 2023, Kuaishou engineers presented cutting‑edge solutions ranging from video quality assessment and enhancement to digital‑human live streaming, custom performance‑optimization frameworks, large‑scale recommendation model acceleration, and multimodal massive‑model deployment for short‑video applications.

Multimodal Large Modelsai-optimizationdigital human

0 likes · 9 min read

How Kuaishou Elevates Short‑Video Quality and AI Performance at NVIDIA GTC 2023

Kuaishou Audio & Video Technology

Dec 30, 2022 · Artificial Intelligence

Unlocking Realistic Bokeh: Depth‑Aware Algorithms Behind Holiday Video Effects

This article explains the optical principles of bokeh (scatter blur), describes a depth‑aware variable‑focus algorithm developed by Kuaishou’s audio‑video team, and details practical optimizations such as saliency detection, edge‑preserving weighting, and adaptive spot‑light effects that enable realistic, customizable holiday video filters.

BokehDepth EstimationVideo Effects

0 likes · 11 min read

Unlocking Realistic Bokeh: Depth‑Aware Algorithms Behind Holiday Video Effects

Kuaishou Audio & Video Technology

Oct 14, 2022 · Artificial Intelligence

How Probability-Driven Adaptive Streaming Won the ACM MM 2022 Grand Challenge

The Kuaishou audio‑video team’s PDAS algorithm, a probability‑driven adaptive streaming solution for short videos, achieved first place at ACM MM 2022 by modeling user behavior, optimizing pre‑load decisions, and delivering superior QoE while minimizing bandwidth waste.

ACM MM 2022QoE optimizationadaptive streaming

0 likes · 12 min read

How Probability-Driven Adaptive Streaming Won the ACM MM 2022 Grand Challenge

Kuaishou Audio & Video Technology

Sep 29, 2022 · Artificial Intelligence

How DeViT Revolutionizes Video Inpainting with Deformed Vision Transformers

The article introduces DeViT, a novel Deformed Vision Transformer framework for video inpainting that leverages a deformable patch homography estimator, mask‑pruned attention, and spatio‑temporal weight adaptation, achieving state‑of‑the‑art results on benchmark datasets and highlighting its potential for advanced video editing tools.

DeViTMultimediaTransformer

0 likes · 10 min read

How DeViT Revolutionizes Video Inpainting with Deformed Vision Transformers