Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Boosting Neural Representations for Videos with a Conditional Decoder

About

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their representation capabilities, primarily due to inadequate alignment of intermediate features during target frame decoding. This paper introduces a universal boosting framework for current implicit video representation approaches. Specifically, we utilize a conditional decoder with a temporal-aware affine transform module, which uses the frame index as a prior condition to effectively align intermediate features with target frames. Besides, we introduce a sinusoidal NeRV-like block to generate diverse intermediate features and achieve a more balanced parameter distribution, thereby enhancing the model's capacity. With a high-frequency information-preserving reconstruction loss, our approach successfully boosts multiple baseline INRs in the reconstruction quality and convergence speed for video regression, and exhibits superior inpainting and interpolation results. Further, we integrate a consistent entropy minimization technique and develop video codecs based on these boosted INRs. Experiments on the UVG dataset confirm that our enhanced codecs significantly outperform baseline INRs and offer competitive rate-distortion performance compared to traditional and learning-based codecs. Code is available at https://github.com/Xinjie-Q/Boosting-NeRV.

Xinjie Zhang, Ren Yang, Dailan He, Xingtong Ge, Tongda Xu, Yan Wang, Hongwei Qin, Jun Zhang• 2024

Related benchmarks

TaskDatasetResultRank
Video InpaintingDAVIS (test)
PSNR35.8
54
Video CompressionUVG
BD-Rate (PSNR)-65.4
49
Video CompressionHEVC ClassB
BD-Rate (MS-SSIM)-86.4
17
Video RegressionUVG 19 (test)
Bea. PSNR34.18
10
Video RegressionHEVC ClassB 14 (test)
PSNR (Bas)31.17
10
Video CompressionBQTerrace
Encoding Time130
7
Video RegressionHEVC ClassB 12
Bas31.17
6
Video InterpolationUVG (test)
PSNR30.6
4
Video InterpolationDAVIS (test)
PSNR21.6
4
Video RegressionJVET Class S2 6K-resolution 360-degree videos
PSNR24.74
3
Showing 10 of 12 rows

Other info

Follow for update