no code implementations • 23 Nov 2024 • Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser, Takahiro Shirakawa, Ko Watanabe, Andreas Dengel, Jinjia Zhou
To address this limitation, we present a novel Training-Free Chroma Key Content Generation Diffusion Model (TKG-DM), which optimizes the initial random noise to produce images with foreground objects on a specifiable color background.
no code implementations • 16 Nov 2024 • Qi Wang, Jinjia Zhou
Recent research on logit distillation has primarily focused on maximizing the information learned from the teacher model's logits to enhance the performance of the student model.
no code implementations • 15 Nov 2024 • Kosuke Iwama, Ryugo Morita, Jinjia Zhou
To further reduce the sampled data while keeping the video quality, this paper explores the temporal redundancy in video CS and proposes a block based adaptive compressive sensing framework with a sampling rate (SR) control strategy.
no code implementations • 15 Nov 2024 • Mizuki Miyamoto, Ryugo Morita, Jinjia Zhou
After that, we use Visual Question Answering(VQA) to measure the relevance of the generated images to the input text, which allows for a more detailed evaluation of the alignment compared to existing methods.
no code implementations • 17 Sep 2024 • Ryugo Morita, Hitoshi Nishimura, Ko Watanabe, Andreas Dengel, Jinjia Zhou
In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research.
no code implementations • 12 Sep 2024 • Xinlei Huang, Jialiang Tang, Xubin Zheng, Jinjia Zhou, Wenxin Yu, Ning Jiang
Consequently, the teacher network can provide balanced and accurate knowledge to train a reliable student network.
no code implementations • 11 Aug 2023 • Ryugo Morita, Zhiqiang Zhang, Jinjia Zhou
We proposed a Background-Aware Text to Image synthesis and manipulation Network (BATINet), which contains two key components: Position Detect Network (PDN) and Harmonize Network (HN).
no code implementations • 25 Nov 2022 • Ryugo Morita, Zhiqiang Zhang, Man M. Ho, Jinjia Zhou
To solve these problems, we propose a novel image manipulation method that interactively edits an image using complex text instructions.
no code implementations • 14 Aug 2022 • Gang He, Shaoyi Long, Li Xu, Chang Wu, Jinjia Zhou, Ming Sun, Xing Wen, Yurong Dai
Joint super-resolution and inverse tone-mapping (SR-ITM) aims to enhance the visual quality of videos that have quality deficiencies in resolution and dynamic range.
1 code implementation • 15 Dec 2021 • Li Xu, Gang He, Jinjia Zhou, Jie Lei, Weiying Xie, Yunsong Li, Yu-Wing Tai
In most video platforms, such as Youtube, and TikTok, the played videos usually have undergone multiple video encodings such as hardware encoding by recording devices, software encoding by video editing apps, and single/multiple video transcoding by video application servers.
no code implementations • 10 Oct 2021 • Jiayao Xu, Chen Fu, Zhiqiang Zhang, Jinjia Zhou
The choice of sensing matrix, the implementation of DP and LSP.
no code implementations • 3 Aug 2021 • Bowen Huang, Xiao Yan, Jinjia Zhou, Yibo Fan
Most deep network methods for compressive sensing reconstruction suffer from the black-box characteristic of DNN.
1 code implementation • 14 Jul 2021 • Trinh Man Hoang, Jinjia Zhou
COVID-19 leads to the high demand for remote interactive systems ever seen.
1 code implementation • 11 Feb 2021 • Man M. Ho, Jinjia Zhou
Second, we simulate many different variants of the real-world degradation using low-level image transformation to gain a generalization in smartphone-scanned image properties, then train a degradation network to generalize all styles of degradation and provide pseudo-scanned photos for unscanned images as if they were scanned by a smartphone.
1 code implementation • 24 Jan 2021 • Trinh Man Hoang, Jinjia Zhou, Yibo Fan
In recent years, layered image compression is demonstrated to be a promising direction, which encodes a compact representation of the input image and apply an up-sampling network to reconstruct the image.
1 code implementation • 22 Jan 2021 • Trinh Man Hoang, Jinjia Zhou
In this paper, we design a neural network to enhance the quality of the compressed frame by leveraging the block information, called B-DRRN (Deep Recursive Residual Network with Block information).
1 code implementation • 21 Jul 2020 • Man M. Ho, Jinjia Zhou
It is designed to 1) generalize the features representing the color transformation from content with natural colors to retouched reference, then blend it into the contextual features of content, 2) predict hyper-parameters (settings or preset) of the applied low-level color transformation methods, 3) stylize content to have a similar color style as reference.
1 code implementation • 13 Jun 2020 • Man M. Ho, Lu Zhang, Alexander Raake, Jinjia Zhou
As a human experience in colorization, our brains first detect and recognize the objects in the photo, then imagine their plausible colors based on many similar objects we have seen in real life, and finally colorize them, as described in the teaser.