10th European Workshop on Visual Information Processing (EUVIP)
September 11-14, 2022 | Lisbon, Portugal
[PDF]
Hadi Amirpour (Alpen-Adria-Universität Klagenfurt), Christine Guillemot (INRIA, France), and Christian Timmerer (Alpen-Adria-Universität Klagenfurt)
Abstract:
Light fields are typically represented by multi-view images and enable post-capture
actions such as refocusing and perspective shift. To compress a light field image, its view images are typically converted into a pseudo video sequence (PVS) and the generated PVS is compressed using a video codec. However, when using the inter-coding tool of a video codec to exploit the redundancy among view images, the possibility to randomly access any view image is lost. On the other hand, when video codecs independently encode view images using the intra-coding tool, random access to view images is enabled, however, at the expense of a significant drop in the compression efficiency. To address this trade-off, we propose to use neural representations to represent 4D light fields. For each light field, a multi-layer perceptron (MLP) is trained to map the light field four dimensions to the color space, thus enabling random access even to pixels. To achieve higher compression efficiency, neural network compression techniques are deployed. The proposed method outperforms the compression efficiency of HEVC inter-coding, while providing random access to view images and even pixel values.
Abstract: In general, manipulated videos will eventually undergo recompression. Video transcoding will occur when the standard of recompression is different from the prior standard. Therefore, as a special sign of recompression, video transcoding can also be considered evidence of forgery in video forensics. In this paper, we focus on the detection and localization of video transcoding from AVC to HEVC (AVC-HEVC). There are two probable cases of AVC-HEVC transcoding – whole video transcoding and partial frame transcoding. However, the existing forensic methods only consider the detection of whole video transcoding, and they do not consider partial frame transcoding localization. In view of this, we propose a framewise scheme based on a convolutional neural network. First, we analyze that the essential difference between AVC-HEVC and HEVC is reflected in the high-frequency components of decoded frames. Then, the partition and location information of prediction units (PUs) are introduced to generate frame-level PU maps to make full use of the local artifacts of PUs. Finally, taking the decoded frames and PU maps as inputs, a dual-path network including specific convolutional modules and an adaptive fusion module is proposed. Through it, the artifacts on a single frame can be better extracted, and the transcoded frames can be detected and localized. Coupled with a simple voting strategy, the results of whole transcoding detection can be easily obtained. A large number of experiments are conducted to verify the performances. The results show that the proposed scheme outperforms or rivals the state-of-the-art methods in AVC-HEVC transcoding detection and localization.
Hadi Amirpour is a postdoc research fellow at ATHENA directed by Prof. Christian Timmerer. He received his B.Sc. degrees in Electrical and Biomedical Engineering, and he pursued his M.Sc. in Electrical Engineering. He got his Ph.D. in computer science from the University of Klagenfurt in 2022. He was appointed co-chair of Task Force 7 (TF7) Immersive Media Experience (IMEx) at the 15th Qualinet meeting. He was involved in the project EmergIMG, a Portuguese consortium on emerging imaging technologies, funded by the Portuguese funding agency and H2020. Currently, he is working on the ATHENA project in cooperation with its industry partner Bitmovin. His research interests are image processing and compression, video processing and compression, quality of experience, emerging 3D imaging technology, and medical image analysis.
Join us at the Institute of Science and Technology Austria (ISTA) in Vienna on June 21.
