no code implementations • 11 Apr 2024 • Bo Zhang, Jinli Suo, Qionghai Dai
To unlock the potential of conventional snapshot compressive videography, we propose a novel hybrid "intensity+event" imaging scheme by incorporating an event camera into a video SCI setup.
no code implementations • 28 Feb 2024 • Meidai Xuanyuan, Yuwang Wang, Honglei Guo, Qionghai Dai
To achieve this, we provide a two-stage and cross-modal controllable video generation pipeline, taking facial landmarks as an explicit and compact control signal to bridge the driving audio, talking context and generated videos.
no code implementations • 6 Jan 2024 • Bo Zhang, Yuqi Han, Jinli Suo, Qionghai Dai
Event cameras or dynamic vision sensors (DVS) record asynchronous response to brightness changes instead of conventional intensity frames, and feature ultra-high sensitivity at low bandwidth.
1 code implementation • 22 Nov 2023 • Zhihong Zhang, Runzhao Yang, Jinli Suo, Yuxiao Cheng, Qionghai Dai
In this work, by leveraging classical coded exposure imaging technique and emerging implicit neural representation for videos, we tactfully embed the motion direction cues into the blurry image during the imaging process and develop a novel self-recursive neural network to sequentially retrieve the latent video sequence from the blurry image utilizing the embedded motion direction cues.
no code implementations • ICCV 2023 • Haiyang Ying, Baowei Jiang, Jinzhi Zhang, Di Xu, Tao Yu, Qionghai Dai, Lu Fang
This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality.
no code implementations • 4 Sep 2023 • Xiaohang Yu, Haoxiang Wang, Yuqi Han, Lei Yang, Tao Yu, Qionghai Dai
This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation.
1 code implementation • 17 May 2023 • Tingxiong Xiao, Runzhao Yang, Yuxiao Cheng, Jinli Suo, Qionghai Dai
Solving partial differential equations (PDEs) has been a fundamental problem in computational science and of wide applications for both scientific and engineering research.
no code implementations • 26 Apr 2023 • Yuqi Han, Tao Yu, Xiaohang Yu, Yuwang Wang, Qionghai Dai
Given multi-view low-resolution images, Super-NeRF constructs a consistency-controlling super-resolution module to generate view-consistent high-resolution details for NeRF.
no code implementations • 9 Apr 2023 • Meidai Xuanyuan, Yuwang Wang, Honglei Guo, Xiao Ma, Yuchen Guo, Tao Yu, Qionghai Dai
To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character Dataset (DPCD), from TV shows.
1 code implementation • 15 Feb 2023 • Yuxiao Cheng, Runzhao Yang, Tingxiong Xiao, Zongren Li, Jinli Suo, Kunlun He, Qionghai Dai
Causal discovery from time-series data has been a central task in machine learning.
no code implementations • 16 Jan 2023 • Bo Zhang, Yuchen Guo, Runzhao Yang, Zhihong Zhang, Jiayi Xie, Jinli Suo, Qionghai Dai
In this paper, we contribute the first multi-illuminance, multi-camera, and low-light dataset, named DarkVision, serving for both image enhancement and object detection.
no code implementations • 9 Dec 2022 • Tao Yan, Maoqi Zhang, Sen Wan, Kaifeng Shang, Haiou Zhang, Xun Cao, Xing Lin, Qionghai Dai
Here, we propose the EEG opto-processor based on diffractive photonic computing units (DPUs) to effectively process the extracranial and intracranial EEG signals and perform epileptic seizure detection.
1 code implementation • CVPR 2023 • Runzhao Yang, Tingxiong Xiao, Yuxiao Cheng, Jinli Suo, Qionghai Dai
In this paper, we propose a Tree-structured Implicit Neural Compression (TINC) to conduct compact representation for local regions and extract the shared features of these local representations in a hierarchical manner.
1 code implementation • 30 Sep 2022 • Runzhao Yang, Tingxiong Xiao, Yuxiao Cheng, Qianni Cao, Jinyuan Qu, Jinli Suo, Qionghai Dai
To address this issue, we firstly derive a mathematical explanation for INR's spectrum concentration property and an analytical insight on the design of INR based compressor.
no code implementations • 26 Sep 2022 • Yun Zhao, Hang Chen, Min Lin, Haiou Zhang, Tao Yan, Xing Lin, Ruqi Huang, Qionghai Dai
Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance.
1 code implementation • 17 Jul 2022 • Zhihong Zhang, Yuxiao Cheng, Jinli Suo, Liheng Bian, Qionghai Dai
In terms of algorithm design, INFWIDE proposes a two-branch architecture, which explicitly removes noise and hallucinates saturated regions in the image space and suppresses ringing artifacts in the feature space, and integrates the two complementary outputs with a subtle multi-scale fusion network for high quality night photograph deblurring.
no code implementations • 23 Apr 2022 • Tao Yan, Rui Yang, Ziyang Zheng, Xing Lin, Hongkai Xiong, Qionghai Dai
Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance.
no code implementations • 11 Apr 2022 • Yuxiao Cheng, Runzhao Yang, Zhihong Zhang, Jinli Suo, Qionghai Dai
In this paper, we propose to build a dual-sensor camera to additionally collect the photons in NIR wavelength, and make use of the correlation between RGB and near-infrared (NIR) spectrum to perform high-quality reconstruction from noisy dark video pairs.
no code implementations • 18 Sep 2021 • Jinli Suo, Weihang Zhang, Jin Gong, Xin Yuan, David J. Brady, Qionghai Dai
Signal capture stands in the forefront to perceive and understand the environment and thus imaging plays the pivotal role in mobile vision.
no code implementations • 3 Jul 2021 • Shiqi Xu, Xi Yang, Wenhui Liu, Joakim Jonsson, Ruobing Qian, Pavan Chandra Konda, Kevin C. Zhou, Lucas Kreiss, Qionghai Dai, Haoqian Wang, Edouard Berrocal, Roarke Horstmeyer
Noninvasive optical imaging through dynamic scattering media has numerous important biomedical applications but still remains a challenging task.
1 code implementation • 30 Jun 2021 • Zhihong Zhang, Chao Deng, Yang Liu, Xin Yuan, Jinli Suo, Qionghai Dai
Towards this end, snapshot compressive imaging (SCI) was proposed as a promising solution to improve the throughput of imaging systems by compressive sampling and computational reconstruction.
no code implementations • CVPR 2021 • Tao Yu, Zerong Zheng, Kaiwen Guo, Pengpeng Liu, Qionghai Dai, Yebin Liu
Human volumetric capture is a long-standing topic in computer vision and computer graphics.
no code implementations • ICCV 2021 • Yang Zheng, Ruizhi Shao, Yuxiang Zhang, Tao Yu, Zerong Zheng, Qionghai Dai, Yebin Liu
We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras.
1 code implementation • ICCV 2021 • Xiu Li, Jinli Suo, Weihang Zhang, Xin Yuan, Qionghai Dai
High quality imaging usually requires bulky and expensive lenses to compensate geometric and chromatic aberrations.
1 code implementation • 24 Mar 2021 • Gaochang Wu, Yebin Liu, Lu Fang, Qionghai Dai, Tianyou Chai
The main problem in direct reconstruction on the EPI involves an information asymmetry between the spatial and angular dimensions, where the detailed portion in the angular dimensions is damaged by undersampling.
1 code implementation • 13 Jan 2021 • Xin Yuan, Yang Liu, Jinli Suo, Frédo Durand, Qionghai Dai
On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm.
1 code implementation • 13 Dec 2020 • Kun Li, Jinsong Zhang, Yebin Liu, Yu-Kun Lai, Qionghai Dai
In each block, we propose a pose-guided non-local attention (PoNA) mechanism with a long-range dependency scheme to select more important regions of image features to transfer.
1 code implementation • CVPR 2021 • Zerong Zheng, Tao Yu, Qionghai Dai, Yebin Liu
Deep implicit functions (DIFs), as a kind of 3D shape representation, are becoming more and more popular in the 3D vision community due to their compactness and strong representation power.
no code implementations • 26 Aug 2020 • Tiankuang Zhou, Xing Lin, Jiamin Wu, Yitong Chen, Hao Xie, Yipeng Li, Jintao Fan, Huaqiang Wu, Lu Fang, Qionghai Dai
Here, we propose an optoelectronic reconfigurable computing paradigm by constructing a diffractive processing unit (DPU) that can efficiently support different neural networks and achieve a high model complexity with millions of neurons.
1 code implementation • 8 Jul 2020 • Zerong Zheng, Tao Yu, Yebin Liu, Qionghai Dai
To overcome the limitations of regular 3D representations, we propose Parametric Model-Conditioned Implicit Representation (PaMIR), which combines the parametric body model with the free-form deep implicit function.
Ranked #2 on 3D Human Reconstruction on CAPE
1 code implementation • 26 May 2020 • Mengqi Ji, Jinzhi Zhang, Qionghai Dai, Lu Fang
Furthermore, the latter problem is handled via a multi-scale strategy that consequently refines the recovered geometry around the region with the repeating pattern.
3 code implementations • CVPR 2020 • Xin Yuan, Yang Liu, Jinli Suo, Qionghai Dai
Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in a single snapshot.
no code implementations • CVPR 2020 • Xueyang Wang, Xiya Zhang, Yinheng Zhu, Yuchen Guo, Xiaoyun Yuan, Liuyu Xiang, Zerun Wang, Guiguang Ding, David J. Brady, Qionghai Dai, Lu Fang
We believe PANDA will contribute to the community of artificial intelligence and praxeology by understanding human behaviors and interactions in large-scale real-world scenes.
no code implementations • 11 Aug 2019 • Haoqian Wang, Zhiwei Xu, Jun Xu, Wangpeng An, Lei Zhang, Qionghai Dai
There are two main problems in label inference: how to measure the confidence of the unlabeled data and how to generalize the classifier.
no code implementations • CVPR 2019 • Tao Yu, Zerong Zheng, Yuan Zhong, Jianhui Zhao, Qionghai Dai, Gerard Pons-Moll, Yebin Liu
This paper proposes a new method for live free-viewpoint human performance capture with dynamic details (e. g., cloth wrinkles) using a single RGBD camera.
1 code implementation • ICCV 2019 • Zerong Zheng, Tao Yu, Yixuan Wei, Qionghai Dai, Yebin Liu
We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D human reconstruction from a single RGB image.
no code implementations • 5 Dec 2018 • Xiu Li, Yebin Liu, Hanbyul Joo, Qionghai Dai, Yaser Sheikh
Specifically, we first introduce a novel markerless motion capture method that can take advantage of dense parsing capability provided by the dense pose detector.
no code implementations • ECCV 2018 • Zerong Zheng, Tao Yu, Hao Li, Kaiwen Guo, Qionghai Dai, Lu Fang, Yebin Liu
We propose a light-weight and highly robust real-time human performance capture method based on a single depth camera and sparse inertial measurement units (IMUs).
3 code implementations • 20 Jul 2018 • Yang Liu, Xin Yuan, Jinli Suo, David J. Brady, Qionghai Dai
We further investigate the special structure of the sampling process in SCI to tackle the computational workload and memory issues in SCI reconstruction.
3 code implementations • CVPR 2018 • Wangpeng An, Haoqian Wang, Qingyun Sun, Jun Xu, Qionghai Dai, Lei Zhang
We first reveal the intrinsic connections between SGD-Momentum and PID based controller, then present the optimization algorithm which exploits the past, current, and change of gradients to update the network parameters.
no code implementations • CVPR 2018 • Tao Yu, Zerong Zheng, Kaiwen Guo, Jianhui Zhao, Qionghai Dai, Hao Li, Gerard Pons-Moll, Yebin Liu
We further propose a joint motion tracking method based on the double layer representation to enable robust and fast motion tracking performance.
1 code implementation • 14 Dec 2017 • Karl Zhanghao, Xingye Chen, Wenhui Liu, Meiqi Li, Chunyan Shan, Xiao Wang, Kun Zhao, Amit Lai, Hao Xie, Qionghai Dai, Peng Xi
The dipole nature of chromophore is important for both super-resolution microscopy and imaging molecular structure, which is nevertheless neglected in most microscopies, even including structured illumination microscopy (SIM) with polarized excitations.
Optics
no code implementations • ICCV 2017 • Tao Yu, Kaiwen Guo, Feng Xu, Yuan Dong, Zhaoqi Su, Jianhui Zhao, Jianguo Li, Qionghai Dai, Yebin Liu
To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method.
no code implementations • 11 Jul 2017 • Liheng Bian, Jinli Suo, Qionghai Dai, Feng Chen
Various algorithms have been proposed for SPI reconstruction, including the linear correlation methods, the alternating projection method (AP), and the compressive sensing based methods.
no code implementations • CVPR 2017 • Gaochang Wu, Mandan Zhao, Liangyong Wang, Qionghai Dai, Tianyou Chai, Yebin Liu
In this paper, we take advantage of the clear texture structure of the epipolar plane image (EPI) in the light field data and model the problem of light field reconstruction from a sparse set of views as a CNN-based angular detail restoration on EPI.
no code implementations • 29 Oct 2016 • Lan Xu, Lu Fang, Wei Cheng, Kaiwen Guo, Guyue Zhou, Qionghai Dai, Yebin Liu
We propose a novel non-rigid surface registration method to track and fuse the depth of the three flying cameras for surface motion tracking of the moving target, and simultaneously calculate the pose of each flying camera.
no code implementations • 1 Mar 2016 • Liheng Bian, Jinli Suo, Jaebum Chung, Xiaoze Ou, Changhuei Yang, Feng Chen, Qionghai Dai
Fourier ptychographic microscopy (FPM) is a novel computational coherent imaging technique for high space-bandwidth product imaging.
no code implementations • 1 Dec 2015 • Dongsheng An, Jinli Suo, Xiangyang Ji, Haoqian Wang, Qionghai Dai
Specifically, this paper derives a normalized dichromatic model for the pixels with identical diffuse color: a unit circle equation of projection coefficients in two subspaces that are orthogonal to and parallel with the illumination, respectively.
no code implementations • ICCV 2015 • Kaiwen Guo, Feng Xu, Yangang Wang, Yebin Liu, Qionghai Dai
We present a new motion tracking method to robustly reconstruct non-rigid geometries and motions from single view depth inputs captured by a consumer depth sensor.
no code implementations • 3 Sep 2015 • Zhaofei Yu, Feng Chen, Jianwu Dong, Qionghai Dai
Although the Bayesian causal inference model explains the problem of causal inference in cue combination successfully, how causal inference in cue combination could be implemented by neural circuits, is unclear.
no code implementations • 19 Jun 2015 • Xuehui Wang, Jinli Suo, Jingyi Yu, Yongdong Zhang, Qionghai Dai
Firstly, we capture the scene with a pinhole and analyze the scene content to determine primary edge orientations.
no code implementations • CVPR 2015 • Tao Yue, Jinli Suo, Jue Wang, Xun Cao, Qionghai Dai
Furthermore, by investigating the visual artifacts of aberration degenerated images captured by consumer-level cameras, the non-uniform distribution of sharpness across color channels and the image lattice is exploited as visual priors, resulting in a novel strategy to utilize the guidance from the sharpest channel and local image regions to improve the overall performance and robustness.
no code implementations • CVPR 2015 • Zhoutong Zhang, Yebin Liu, Qionghai Dai
We first introduce a disparity assisted phase based synthesis (DAPS) strategy that can integrate disparity infor- mation into the phase term of a reference image to warp it to its close neighbor views.
no code implementations • CVPR 2014 • Jingyu Lin, Yebin Liu, Matthias B. Hullin, Qionghai Dai
A transient image is the optical impulse response of a scene which visualizes light propagation during an ultra-short time interval.
no code implementations • CVPR 2014 • Chenguang Ma, Xing Lin, Jinli Suo, Qionghai Dai, Gordon Wetzstein
Capturing and understanding visual signals is one of the core interests of computer vision.
no code implementations • 6 Dec 2013 • Liheng Bian, Jinli Suo, Feng Chen, Qionghai Dai
Optical coherence tomography (OCT) is an important interferometric diagnostic technique which provides cross-sectional views of the subsurface microstructure of biological tissues.