FrameCorr: Adaptive, Autoencoder-based Neural Compression for Video Reconstruction in Resource and Timing Constrained Network Settings

• URL: http://arxiv.org/abs/2409.02453v2
• Date: Tue, 10 Sep 2024 08:20:36 GMT
• Title: FrameCorr: Adaptive, Autoencoder-based Neural Compression for Video Reconstruction in Resource and Timing Constrained Network Settings
• Authors: John Li, Shehab Sarar Ahmed, Deepak Nair,
• Abstract summary: Existing video compression methods face difficulties in recovering compressed data when incomplete data is provided. We introduce FrameCorr, a deep-learning based solution that utilizes previously received data to predict the missing segments of a frame.
• Score: 0.18906710320196732
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the growing adoption of video processing via Internet of Things (IoT) devices due to their cost-effectiveness, transmitting captured data to nearby servers poses challenges due to varying timing constraints and scarcity of network bandwidth. Existing video compression methods face difficulties in recovering compressed data when incomplete data is provided. Here, we introduce FrameCorr, a deep-learning based solution that utilizes previously received data to predict the missing segments of a frame, enabling the reconstruction of a frame from partially received data.

Related papers

• VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data [18.877077302923713]
  We present a video compression-based degradation model to synthesize low-resolution image data in the blind SISR task. Our proposed image synthesizing method is widely applicable to existing image datasets. By introducing video coding artifacts to SISR degradation models, neural networks can super-resolve images with the ability to restore video compression degradations.
  arXiv  Detail & Related papers  (2023-11-02T05:24:19Z)
• Reparo: Loss-Resilient Generative Codec for Video Conferencing [26.908731561652726]
  We introduce Reparo, a loss-resilient video conferencing framework based on generative deep learning models. We show that Reparo outperforms state-of-the-art FEC-based video conferencing solutions in terms of both video quality (measured through PSNR, SSIM, and LPIPS) and the occurrence of video freezes.
  arXiv  Detail & Related papers  (2023-05-23T14:58:09Z)
• GRACE: Loss-Resilient Real-Time Video through Neural Codecs [31.006987868475683]
  In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements. We present a loss-resilient real-time video system called GRACE, which preserves the user's quality of experience (QE) across a wide range of packet losses.
  arXiv  Detail & Related papers  (2023-05-21T03:50:44Z)
• NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression [19.88538977373161]
  Deep learning-based video compression methods are replacing traditional algorithms and providing state-of-the-art results on edge devices. We present a real-world LED attack crafted to target video compression frameworks. Our physically realizable attack, dubbed NetFlick, can degrade temporal correlation between successive frames by injecting flickering temporal perturbations. In addition, we propose universal perturbations that can downgrade performance of incoming video without prior knowledge of the contents.
  arXiv  Detail & Related papers  (2023-04-04T01:29:51Z)
• Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications [78.55896581882595]
  Lossy image compression techniques can reduce the quality of the images, leading to accuracy degradation. In this paper, we analyze the effect of applying low-overhead lossy image compression methods on the accuracy of visual crowd counting.
  arXiv  Detail & Related papers  (2022-07-20T19:20:03Z)
• Learned Video Compression via Heterogeneous Deformable Compensation Network [78.72508633457392]
  We propose a learned video compression framework via heterogeneous deformable compensation strategy (HDCVC) to tackle the problems of unstable compression performance. More specifically, the proposed algorithm extracts features from the two adjacent frames to estimate content-Neighborhood heterogeneous deformable (HetDeform) kernel offsets. Experimental results indicate that HDCVC achieves superior performance than the recent state-of-the-art learned video compression approaches.
  arXiv  Detail & Related papers  (2022-07-11T02:31:31Z)
• Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
  Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks. We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
  arXiv  Detail & Related papers  (2022-02-09T18:48:02Z)
• Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement [74.1052624663082]
  We develop a deep learning architecture capable of restoring detail to compressed videos. We show that this improves restoration accuracy compared to prior compression correction methods. We condition our model on quantization data which is readily available in the bitstream.
  arXiv  Detail & Related papers  (2022-01-31T18:56:04Z)
• COMISR: Compression-Informed Video Super-Resolution [76.94152284740858]
  Most videos on the web or mobile devices are compressed, and the compression can be severe when the bandwidth is limited. We propose a new compression-informed video super-resolution model to restore high-resolution content without introducing artifacts caused by compression.
  arXiv  Detail & Related papers  (2021-05-04T01:24:44Z)
• Ultra-low bitrate video conferencing using deep image animation [7.263312285502382]
  We propose a novel deep learning approach for ultra-low video compression for video conferencing applications. We employ deep neural networks to encode motion information as keypoint displacement and reconstruct the video signal at the decoder side.
  arXiv  Detail & Related papers  (2020-12-01T09:06:34Z)
• Content Adaptive and Error Propagation Aware Deep Video Compression [110.31693187153084]
  We propose a content adaptive and error propagation aware video compression system. Our method employs a joint training strategy by considering the compression performance of multiple consecutive frames instead of a single frame. Instead of using the hand-crafted coding modes in the traditional compression systems, we design an online encoder updating scheme in our system.
  arXiv  Detail & Related papers  (2020-03-25T09:04:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.