Real-time Streaming Video Denoising with Bidirectional Buffers

14 Jul 2022  ·  Chenyang Qi, Junming Chen, Xin Yang, Qifeng Chen ·

Video streams are delivered continuously to save the cost of storage and device memory. Real-time denoising algorithms are typically adopted on the user device to remove the noise involved during the shooting and transmission of video streams. However, sliding-window-based methods feed multiple input frames for a single output and lack computation efficiency. Recent multi-output inference works propagate the bidirectional temporal feature with a parallel or recurrent framework, which either suffers from performance drops on the temporal edges of clips or can not achieve online inference. In this paper, we propose a Bidirectional Streaming Video Denoising (BSVD) framework, to achieve high-fidelity real-time denoising for streaming videos with both past and future temporal receptive fields. The bidirectional temporal fusion for online inference is considered not applicable in the MoViNet. However, we introduce a novel Bidirectional Buffer Block as the core module of our BSVD, which makes it possible during our pipeline-style inference. In addition, our method is concise and flexible to be utilized in both non-blind and blind video denoising. We compare our model with various state-of-the-art video denoising models qualitatively and quantitatively on synthetic and real noise. Our method outperforms previous methods in terms of restoration fidelity and runtime. Our source code is publicly available at

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Video Denoising CRVD BSVD (real-time) PSNR (Raw) 44.39 # 1
SSIM (Raw) 0.9894 # 1
PSNR (sRBG) 40.48 # 1
SSIM (sRGB) 0.9820 # 1
Video Denoising DAVIS sigma40 BSVD (real-time) PSNR 33.86 # 4
Video Denoising DAVIS sigma50 BSVD (Real-time) PSNR 32.91 # 4
Video Denoising Set8 sigma40 BSVD (real-time) PSNR 30.97 # 4
Video Denoising Set8 sigma50 BSVD (real-time) PSNR 30.06 # 4