no code implementations • 23 Mar 2024 • Kodai Shimosato, Norimichi Ukita
In our method, this domain gap is resolved by training the inpainting network with object masks extracted by segmentation, and such object masks are also used in the inference step.
no code implementations • 23 Mar 2024 • Masaya Kotani, Takeru Oba, Norimichi Ukita
This paper proposes a depth estimation method using radar-image fusion by addressing the uncertain vertical directions of sparse radar measurements.
no code implementations • 23 Mar 2024 • Hiroshi Mori, Norimichi Ukita
The proposed training strategy stabilizes VSR by training a VSR network with various RNN hidden states changed depending on the video properties.
1 code implementation • 13 Mar 2024 • Yuki Kondo, Riku Miyata, Fuma Yasue, Taito Naruki, Norimichi Ukita
In this paper, we analyze and discuss ShadowFormer in preparation for the NTIRE2023 Shadow Removal Challenge [1], implementing five key improvements: image alignment, the introduction of a perceptual quality loss function, the semi-automatic annotation for shadow detection, joint learning of shadow detection and removal, and the introduction of new data augmentation technique "CutShadow" for shadow removal.
1 code implementation • 5 Mar 2024 • Chihiro Nakatani, Hiroaki Kawashima, Norimichi Ukita
Unlike prior work in which the manual annotation of group activities is required for supervised learning, our method learns the GAF through person attribute prediction without group activity annotations.
1 code implementation • 8 Nov 2023 • Hiromu Taketsugu, Norimichi Ukita
Human Pose (HP) estimation is actively researched because of its wide range of applications.
1 code implementation • ICCV 2023 • Takahiro Maeda, Norimichi Ukita
Safety-critical applications such as autonomous vehicles and social robots require fast computation and accurate probability density estimation on trajectory prediction.
1 code implementation • ICCV 2023 • Chihiro Nakatani, Hiroaki Kawashima, Norimichi Ukita
We introduce a specialized MLP head with positional embedding to the Transformer so that it predicts pixelwise confidence of joint attention for generating the confidence heatmap.
1 code implementation • 18 Jul 2023 • Yuki Kondo, Norimichi Ukita, Takayuki Yamaguchi, Hao-Yu Hou, Mu-Yi Shen, Chia-Chi Hsu, En-Ming Huang, Yu-Chen Huang, Yu-Cheng Xia, Chien-Yao Wang, Chun-Yi Lee, Da Huo, Marc A. Kastner, TingWei Liu, Yasutomo Kawanishi, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide, Yosuke Shinya, Xinyao Liu, Guang Liang, Syusuke Yasui
Small Object Detection (SOD) is an important machine vision topic because (i) a variety of real-world applications require object detection for distant objects and (ii) SOD is a challenging task due to the noisy, blurred, and less-informative image appearances of small objects.
Ranked #2 on Small Object Detection on SOD4SB Public Test (using extra training data)
no code implementations • 15 Jun 2023 • Takeru Oba, Norimichi Ukita
In R2-Diff, a motion retrieved from a dataset based on image similarity is fed into a diffusion model instead of random noise.
1 code implementation • 24 Feb 2023 • Yuki Kondo, Norimichi Ukita
This paper proposes crack segmentation augmented by super resolution (SR) with deep neural networks.
1 code implementation • 22 Feb 2023 • Kaikai Zhao, Norimichi Ukita
We propose a triple-attention module in which the first attention is a plain scaled dot-product attention, the second/third attention generates high-quality weights/values (with the assistance of GT Fg-Bg Mask) and shares the values/weights with the first attention to improve the quality of values/weights.
no code implementations • 16 Feb 2023 • Tomoki Yoshida, Yuki Kondo, Takahiro Maeda, Kazutoshi Akita, Norimichi Ukita
In our second model, the Kernelized BackProjection Network (KBPN), a raw kernel is estimated and directly employed for modeling the image degradation.
no code implementations • 10 Feb 2023 • Takeru Oba, Norimichi Ukita
While our method evaluates the task achievability by the Energy-Based Model (EBM), previous EBMs are not designed for evaluating the consistency between different domains (i. e., image and motion in our method).
1 code implementation • 27 Aug 2022 • Fan Yang, Norimichi Ukita, Sakriani Sakti, Satoshi Nakamura
By using MOT, the spatiotemporal boundary of each actor is obtained and assigned to a unique actor identity.
1 code implementation • CVPR 2022 • Takahiro Maeda, Norimichi Ukita
Our IK-based motion synthesis method allows us to generate a variety of motions semi-automatically.
1 code implementation • International Conference on Machine Vision and Applications (MVA) 2021 • Yuki Kondo, Norimichi Ukita
This paper proposes a method for crack segmentation on low-resolution images.
1 code implementation • MVA 2021 • Chihiro Nakatani, Kohei Sendo, Norimichi Ukita
This paper proposes joint learning of individual action recognition and people grouping for improving group activity recognition.
Ranked #5 on Group Activity Recognition on Volleyball
no code implementations • 7 Jun 2021 • Goutam Bhat, Martin Danelljan, Radu Timofte, Kazutoshi Akita, Wooyeong Cho, Haoqiang Fan, Lanpeng Jia, Daeshik Kim, Bruno Lecouat, Youwei Li, Shuaicheng Liu, Ziluan Liu, Ziwei Luo, Takahiro Maeda, Julien Mairal, Christian Micheloni, Xuan Mo, Takeru Oba, Pavel Ostyakov, Jean Ponce, Sanghyeok Son, Jian Sun, Norimichi Ukita, Rao Muhammad Umer, Youliang Yan, Lei Yu, Magauiya Zhussip, Xueyi Zou
This paper reviews the NTIRE2021 challenge on burst super-resolution.
no code implementations • 14 Sep 2020 • Dario Fuoli, Zhiwu Huang, Shuhang Gu, Radu Timofte, Arnau Raventos, Aryan Esfandiari, Salah Karout, Xuan Xu, Xin Li, Xin Xiong, Jinge Wang, Pablo Navarrete Michelini, Wen-Hao Zhang, Dongyang Zhang, Hanwei Zhu, Dan Xia, Haoyu Chen, Jinjin Gu, Zhi Zhang, Tongtong Zhao, Shanshan Zhao, Kazutoshi Akita, Norimichi Ukita, Hrishikesh P. S, Densen Puthussery, Jiji C. V
Missing information can be restored well in this region, especially in HR videos, where the high-frequency content mostly consists of texture details.
no code implementations • 1 Sep 2020 • Tomoki Yoshida, Kazutoshi Akita, Muhammad Haris, Norimichi Ukita
The previous approaches use several loss functions which is hard to interpret and has the implicit relationships to improve the perceptual score.
no code implementations • 3 May 2020 • Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha, Jiande Jiang, Xinbo Gao, Wen Lu, Jing Liu, Kwangjin Yoon, Taegyun Jeon, Kazutoshi Akita, Takeru Ooba, Norimichi Ukita, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Dongliang He, Wenhao Wu, Yukang Ding, Chao Li, Fu Li, Shilei Wen, Jianwei Li, Fuzhi Yang, Huan Yang, Jianlong Fu, Byung-Hoon Kim, JaeHyun Baek, Jong Chul Ye, Yuchen Fan, Thomas S. Huang, Junyeop Lee, Bokyeung Lee, Jungki Min, Gwantae Kim, Kanghyu Lee, Jaihyun Park, Mykola Mykhailych, Haoyu Zhong, Yukai Shi, Xiaojun Yang, Zhijing Yang, Liang Lin, Tongtong Zhao, Jinjia Peng, Huibing Wang, Zhi Jin, Jiahao Wu, Yifu Chen, Chenming Shang, Huanrong Zhang, Jeongki Min, Hrishikesh P. S, Densen Puthussery, Jiji C. V
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
1 code implementation • CVPR 2020 • Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
We consider the problem of space-time super-resolution (ST-SR): increasing spatial resolution of video frames and simultaneously interpolating frames to increase the frame rate.
no code implementations • 4 Jun 2019 • Norimichi Ukita, Yusuke Uematsu
While the first and second learning schemes select only poses that are similar to those in the supervised training data, the third scheme selects more true-positive poses that are significantly different from any supervised poses.
7 code implementations • 4 Apr 2019 • Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
Previous feed-forward architectures of recently proposed deep super-resolution networks learn the features of low-resolution inputs and the non-linear mapping from those to a high-resolution output.
Ranked #1 on Image Super-Resolution on BSDS100 - 8x upscaling
7 code implementations • CVPR 2019 • Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
We proposed a novel architecture for the problem of video super-resolution.
no code implementations • 26 Jan 2019 • Norimichi Ukita
Human pose estimation in images and videos is one of key technologies for realizing a variety of human activity recognition tasks (e. g., human-computer interaction, gesture recognition, surveillance, and video summarization).
no code implementations • 30 Mar 2018 • Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
We consider how image super resolution (SR) can contribute to an object detection task in low-resolution images.
17 code implementations • CVPR 2018 • Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita
The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output.
Ranked #16 on Video Super-Resolution on Vid4 - 4x upscaling