Qionghai Dai

Runzhao Yang, Tingxiong Xiao, Yuxiao Cheng et al. · tsinghua

Implicit neural representation (INR) can describe the target scenes with high fidelity using a small number of parameters, and is emerging as a promising data compression technique. However, limited spectrum coverage is intrinsic to INR, and it is non-trivial to remove redundancy in diverse complex data effectively. Preliminary studies can only exploit either global or local correlation in the target data and thus of limited performance. 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. Specifically, we use Multi-Layer Perceptrons (MLPs) to fit the partitioned local regions, and these MLPs are organized in tree structure to share parameters according to the spatial distance. The parameter sharing scheme not only ensures the continuity between adjacent regions, but also jointly removes the local and non-local redundancy. Extensive experiments show that TINC improves the compression fidelity of INR, and has shown impressive compression capabilities over commercial tools and other deep learning based methods. Besides, the approach is of high flexibility and can be tailored for different data and parameter settings. The source code can be found at https://github.com/RichealYoung/TINC .

Runzhao Yang, Tingxiong Xiao, Yuxiao Cheng et al. · tsinghua

Massive collection and explosive growth of biomedical data, demands effective compression for efficient storage, transmission and sharing. Readily available visual data compression techniques have been studied extensively but tailored for natural images/videos, and thus show limited performance on biomedical data which are of different features and larger diversity. Emerging implicit neural representation (INR) is gaining momentum and demonstrates high promise for fitting diverse visual data in target-data-specific manner, but a general compression scheme covering diverse biomedical data is so far absent. 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. Further, we propose a Spectrum Concentrated Implicit neural compression (SCI) which adaptively partitions the complex biomedical data into blocks matching INR's concentrated spectrum envelop, and design a funnel shaped neural network capable of representing each block with a small number of parameters. Based on this design, we conduct compression via optimization under given budget and allocate the available parameters with high representation accuracy. The experiments show SCI's superior performance to state-of-the-art methods including commercial compressors, data-driven ones, and INR based counterparts on diverse biomedical data. The source code can be found at https://github.com/RichealYoung/ImplicitNeuralCompression.git.

Zhihong Zhang, Runzhao Yang, Jinli Suo et al. · tsinghua

The demand for compact cameras capable of recording high-speed scenes with high resolution is steadily increasing. However, achieving such capabilities often entails high bandwidth requirements, resulting in bulky, heavy systems unsuitable for low-capacity platforms. To address this challenge, leveraging a coded exposure setup to encode a frame sequence into a blurry snapshot and subsequently retrieve the latent sharp video presents a lightweight solution. Nevertheless, restoring motion from blur remains a formidable challenge due to the inherent ill-posedness of motion blur decomposition, the intrinsic ambiguity in motion direction, and the diverse motions present in natural videos. In this study, we propose a novel approach to address these challenges by combining the classical coded exposure imaging technique with the emerging implicit neural representation for videos. We strategically embed motion direction cues into the blurry image during the imaging process. Additionally, we develop a novel implicit neural representation based blur decomposition network to sequentially extract the latent video frames from the blurry image, leveraging the embedded motion direction cues. To validate the effectiveness and efficiency of our proposed framework, we conduct extensive experiments using benchmark datasets and real-captured blurry images. The results demonstrate that our approach significantly outperforms existing methods in terms of both quality and flexibility. The code for our work is available at .https://github.com/zhihongz/BDINR

Yue Deng, Qionghai Dai, Risheng Liu et al.

Recovering intrinsic data structure from corrupted observations plays an important role in various tasks in the communities of machine learning and signal processing. In this paper, we propose a novel model, named log-sum heuristic recovery (LHR), to learn the essential low-rank structure from corrupted data. Different from traditional approaches, which directly utilize $\ell_1$ norm to measure the sparseness, LHR introduces a more reasonable log-sum measurement to enhance the sparsity in both the intrinsic low-rank structure and in the sparse corruptions. Although the proposed LHR optimization is no longer convex, it still can be effectively solved by a majorization-minimization (MM) type algorithm, with which the non-convex objective function is iteratively replaced by its convex surrogate and LHR finally falls into the general framework of reweighed approaches. We prove that the MM-type algorithm can converge to a stationary point after successive iteration. We test the performance of our proposed model by applying it to solve two typical problems: robust principal component analysis (RPCA) and low-rank representation (LRR). For RPCA, we compare LHR with the benchmark Principal Component Pursuit (PCP) method from both the perspectives of simulations and practical applications. For LRR, we apply LHR to compute the low-rank representation matrix for motion segmentation and stock clustering. Experimental results on low rank structure learning demonstrate that the proposed Log-sum based model performs much better than the $\ell_1$-based method on for data with higher rank and with denser corruptions.

Yuxiao Cheng, Runzhao Yang, Tingxiong Xiao et al. · tsinghua

Causal discovery from time-series data has been a central task in machine learning. Recently, Granger causality inference is gaining momentum due to its good explainability and high compatibility with emerging deep neural networks. However, most existing methods assume structured input data and degenerate greatly when encountering data with randomly missing entries or non-uniform sampling frequencies, which hampers their applications in real scenarios. To address this issue, here we present CUTS, a neural Granger causal discovery algorithm to jointly impute unobserved data points and build causal graphs, via plugging in two mutually boosting modules in an iterative framework: (i) Latent data prediction stage: designs a Delayed Supervision Graph Neural Network (DSGNN) to hallucinate and register unstructured data which might be of high dimension and with complex distribution; (ii) Causal graph fitting stage: builds a causal adjacency matrix with imputed data under sparse penalty. Experiments show that CUTS effectively infers causal graphs from unstructured time-series data, with significantly superior performance to existing methods. Our approach constitutes a promising step towards applying causal discovery to real applications with non-ideal observations.

Zhihong Zhang, Yuxiao Cheng, Jinli Suo et al.

Under low-light environment, handheld photography suffers from severe camera shake under long exposure settings. Although existing deblurring algorithms have shown promising performance on well-exposed blurry images, they still cannot cope with low-light snapshots. Sophisticated noise and saturation regions are two dominating challenges in practical low-light deblurring. In this work, we propose a novel non-blind deblurring method dubbed image and feature space Wiener deconvolution network (INFWIDE) to tackle these problems systematically. 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. For effective network training, we design a set of loss functions integrating a forward imaging model and backward reconstruction to form a close-loop regularization to secure good convergence of the deep neural network. Further, to optimize INFWIDE's applicability in real low-light conditions, a physical-process-based low-light noise model is employed to synthesize realistic noisy night photographs for model training. Taking advantage of the traditional Wiener deconvolution algorithm's physically driven characteristics and arisen deep neural network's representation ability, INFWIDE can recover fine details while suppressing the unpleasant artifacts during deblurring. Extensive experiments on synthetic data and real data demonstrate the superior performance of the proposed approach.

Yuqi Han, Tao Yu, Xiaohang Yu et al.

The neural radiance field (NeRF) achieved remarkable success in modeling 3D scenes and synthesizing high-fidelity novel views. However, existing NeRF-based methods focus more on the make full use of the image resolution to generate novel views, but less considering the generation of details under the limited input resolution. In analogy to the extensive usage of image super-resolution, NeRF super-resolution is an effective way to generate the high-resolution implicit representation of 3D scenes and holds great potential applications. Up to now, such an important topic is still under-explored. In this paper, we propose a NeRF super-resolution method, named Super-NeRF, to generate high-resolution NeRF from only low-resolution inputs. Given multi-view low-resolution images, Super-NeRF constructs a consistency-controlling super-resolution module to generate view-consistent high-resolution details for NeRF. Specifically, an optimizable latent code is introduced for each low-resolution input image to control the 2D super-resolution images to converge to the view-consistent output. The latent codes of each low-resolution image are optimized synergistically with the target Super-NeRF representation to fully utilize the view consistency constraint inherent in NeRF construction. We verify the effectiveness of Super-NeRF on synthetic, real-world, and AI-generated NeRF datasets. Super-NeRF achieves state-of-the-art NeRF super-resolution performance on high-resolution detail generation and cross-view consistency.

Tao Yan, Rui Yang, Ziyang Zheng et al.

Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance. However, existing architectures can only handle data with regular structures, e.g., images or videos, but fail to generalize to graph-structured data beyond Euclidean space, e.g., social networks or document co-citation networks. Here, we propose an all-optical graph representation learning architecture, termed diffractive graph neural network (DGNN), based on the integrated diffractive photonic computing units (DPUs) to address this limitation. Specifically, DGNN optically encodes node attributes into strip optical waveguides, which are transformed by DPUs and aggregated by on-chip optical couplers to extract their feature representations. Each DPU comprises successive passive layers of metalines to modulate the electromagnetic optical field via diffraction, where the metaline structures are learnable parameters shared across graph nodes. DGNN captures complex dependencies among the node neighborhoods and eliminates the nonlinear transition functions during the light-speed optical message passing over graph structures. We demonstrate the use of DGNN extracted features for node and graph-level classification tasks with benchmark databases and achieve superior performance. Our work opens up a new direction for designing application-specific integrated photonic circuits for high-efficiency processing of large-scale graph data structures using deep learning.

Bo Zhang, Yuchen Guo, Runzhao Yang et al.

Imaging and perception in photon-limited scenarios is necessary for various applications, e.g., night surveillance or photography, high-speed photography, and autonomous driving. In these cases, cameras suffer from low signal-to-noise ratio, which degrades the image quality severely and poses challenges for downstream high-level vision tasks like object detection and recognition. Data-driven methods have achieved enormous success in both image restoration and high-level vision tasks. However, the lack of high-quality benchmark dataset with task-specific accurate annotations for photon-limited images/videos delays the research progress heavily. 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. We provide bright and dark pairs with pixel-wise registration, in which the bright counterpart provides reliable reference for restoration and annotation. The dataset consists of bright-dark pairs of 900 static scenes with objects from 15 categories, and 32 dynamic scenes with 4-category objects. For each scene, images/videos were captured at 5 illuminance levels using three cameras of different grades, and average photons can be reliably estimated from the calibration data for quantitative studies. The static-scene images and dynamic videos respectively contain around 7,344 and 320,667 instances in total. With DarkVision, we established baselines for image/video enhancement and object detection by representative algorithms. To demonstrate an exemplary application of DarkVision, we propose two simple yet effective approaches for improving performance in video enhancement and object detection respectively. We believe DarkVision would advance the state-of-the-arts in both imaging and related computer vision tasks in low-light environment.

Tao Yan, Maoqi Zhang, Sen Wan et al.

Electroencephalography (EEG) analysis extracts critical information from brain signals, which has provided fundamental support for various applications, including brain-disease diagnosis and brain-computer interface. However, the real-time processing of large-scale EEG signals at high energy efficiency has placed great challenges for electronic processors on edge computing devices. 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. The signals of EEG channels within a second-time window are optically encoded as inputs to the constructed diffractive neural networks for classification, which monitors the brain state to determine whether it's the symptom of an epileptic seizure or not. We developed both the free-space and integrated DPUs as edge computing systems and demonstrated their applications for real-time epileptic seizure detection with the benchmark datasets, i.e., the CHB-MIT extracranial EEG dataset and Epilepsy-iEEG-Multicenter intracranial EEG dataset, at high computing performance. Along with the channel selection mechanism, both the numerical evaluations and experimental results validated the sufficient high classification accuracies of the proposed opto-processors for supervising the clinical diagnosis. Our work opens up a new research direction of utilizing photonic computing techniques for processing large-scale EEG signals in promoting its broader applications.

Yuduo Guo, Hao Zhang, Mingyu Li et al.

The detection limit of astronomical imaging observations is limited by several noise sources. Some of that noise is correlated between neighbouring image pixels and exposures, so in principle could be learned and corrected. We present an astronomical self-supervised transformer-based denoising algorithm (ASTERIS), that integrates spatiotemporal information across multiple exposures. Benchmarking on mock data indicates that ASTERIS improves detection limits by 1.0 magnitude at 90% completeness and purity, while preserving the point spread function and photometric accuracy. Observational validation using data from the James Webb Space Telescope (JWST) and Subaru telescope identifies previously undetectable features, including low-surface-brightness galaxy structures and gravitationally-lensed arcs. Applied to deep JWST images, ASTERIS identifies three times more redshift > 9 galaxy candidates, with rest-frame ultraviolet luminosity 1.0 magnitude fainter, than previous methods.

Yun Zhao, Hang Chen, Min Lin et al.

Increasing the layer number of on-chip photonic neural networks (PNNs) is essential to improve its model performance. However, the successively cascading of network hidden layers results in larger integrated photonic chip areas. To address this issue, we propose the optical neural ordinary differential equations (ON-ODE) architecture that parameterizes the continuous dynamics of hidden layers with optical ODE solvers. The ON-ODE comprises the PNNs followed by the photonic integrator and optical feedback loop, which can be configured to represent residual neural networks (ResNet) and recurrent neural networks with effectively reduced chip area occupancy. For the interference-based optoelectronic nonlinear hidden layer, the numerical experiments demonstrate that the single hidden layer ON-ODE can achieve approximately the same accuracy as the two-layer optical ResNet in image classification tasks. Besides, the ONODE improves the model classification accuracy for the diffraction-based all-optical linear hidden layer. The time-dependent dynamics property of ON-ODE is further applied for trajectory prediction with high accuracy.

Meidai Xuanyuan, Yuwang Wang, Honglei Guo et al.

Imagine an interesting multimodal interactive scenario that you can see, hear, and chat with an AI-generated digital character, who is capable of behaving like Sheldon from The Big Bang Theory, as a DEEP copy from appearance to personality. Towards this fantastic multimodal chatting scenario, we propose a novel task, named Deep Personalized Character Creation (DPCC): creating multimodal chat personalized characters from multimodal data such as TV shows. Specifically, given a single- or multi-modality input (text, audio, video), the goal of DPCC is to generate a multi-modality (text, audio, video) response, which should be well-matched the personality of a specific character such as Sheldon, and of high quality as well. To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character Dataset (DPCD), from TV shows. DPCD contains character-specific multimodal dialogue data of ~10k utterances and ~6 hours of audio/video per character, which is around 10 times larger compared to existing related datasets.On DPCD, we present a baseline method for the DPCC task and create 5 Deep personalized digital Characters (DeepCharacters) from Big Bang TV Shows. We conduct both subjective and objective experiments to evaluate the multimodal response from DeepCharacters in terms of characterization and quality. The results demonstrates that, on our collected DPCD dataset, the proposed baseline can create personalized digital characters for generating multimodal response.Our collected DPCD dataset, the code of data collection and our baseline will be published soon.

Haiyang Ying, Baowei Jiang, Jinzhi Zhang et al.

This paper proposes a method for fast scene radiance field reconstruction with strong novel view synthesis performance and convenient scene editing functionality. The key idea is to fully utilize semantic parsing and primitive extraction for constraining and accelerating the radiance field reconstruction process. To fulfill this goal, a primitive-aware hybrid rendering strategy was proposed to enjoy the best of both volumetric and primitive rendering. We further contribute a reconstruction pipeline conducts primitive parsing and radiance field learning iteratively for each input frame which successfully fuses semantic, primitive, and radiance information into a single framework. Extensive evaluations demonstrate the fast reconstruction ability, high rendering quality, and convenient editing functionality of our method.

Mengqi Ji, Jinzhi Zhang, Qionghai Dai et al.

Multi-view stereopsis (MVS) tries to recover the 3D model from 2D images. As the observations become sparser, the significant 3D information loss makes the MVS problem more challenging. Instead of only focusing on densely sampled conditions, we investigate sparse-MVS with large baseline angles since the sparser sensation is more practical and more cost-efficient. By investigating various observation sparsities, we show that the classical depth-fusion pipeline becomes powerless for the case with a larger baseline angle that worsens the photo-consistency check. As another line of the solution, we present SurfaceNet+, a volumetric method to handle the 'incompleteness' and the 'inaccuracy' problems induced by a very sparse MVS setup. Specifically, the former problem is handled by a novel volume-wise view selection approach. It owns superiority in selecting valid views while discarding invalid occluded views by considering the geometric prior. Furthermore, the latter problem is handled via a multi-scale strategy that consequently refines the recovered geometry around the region with the repeating pattern. The experiments demonstrate the tremendous performance gap between SurfaceNet+ and state-of-the-art methods in terms of precision and recall. Under the extreme sparse-MVS settings in two datasets, where existing methods can only return very few points, SurfaceNet+ still works as well as in the dense MVS setting. The benchmark and the implementation are publicly available at https://github.com/mjiUST/SurfaceNet-plus.

Xin Yuan, Yang Liu, Jinli Suo et al.

Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in a single snapshot. Though enjoying the advantages of low-bandwidth, low-power and low-cost, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging. The bottleneck lies in the reconstruction algorithms; they are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the widely used PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload and prove the convergence of PnP-GAP under the SCI hardware constraints. By employing deep denoising priors, we first time show that PnP can recover a UHD color video ($3840\times 1644\times 48$ with PNSR above 30dB) from a snapshot 2D measurement. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. The code is available at https://github.com/liuyang12/PnP-SCI.

Bo Zhang, Jinli Suo, Qionghai Dai

Video snapshot compressive imaging (SCI) encodes the target dynamic scene compactly into a snapshot and reconstructs its high-speed frame sequence afterward, greatly reducing the required data footprint and transmission bandwidth as well as enabling high-speed imaging with a low frame rate intensity camera. In implementation, high-speed dynamics are encoded via temporally varying patterns, and only frames at corresponding temporal intervals can be reconstructed, while the dynamics occurring between consecutive frames are lost. 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. Our proposed system consists of a dual-path optical setup to record the coded intensity measurement and intermediate event signals simultaneously, which is compact and photon-efficient by collecting the half photons discarded in conventional video SCI. Correspondingly, we developed a dual-branch Transformer utilizing the reciprocal relationship between two data modes to decode dense video frames. Extensive experiments on both simulated and real-captured data demonstrate our superiority to state-of-the-art video SCI and video frame interpolation (VFI) methods. Benefiting from the new hybrid design leveraging both intrinsic redundancy in videos and the unique feature of event cameras, we achieve high-quality videography at 0.1ms time intervals with a low-cost CMOS image sensor working at 24 FPS.

Bo Zhang, Yuqi Han, Jinli Suo et al.

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. The new mechanism demonstrates great advantages in challenging scenarios with fast motion and large dynamic range. However, the recorded events might be highly sparse due to either limited hardware bandwidth or extreme photon starvation in harsh environments. To unlock the full potential of event cameras, we propose an inventive event sequence completion approach conforming to the unique characteristics of event data in both the processing stage and the output form. Specifically, we treat event streams as 3D event clouds in the spatiotemporal domain, develop a diffusion-based generative model to generate dense clouds in a coarse-to-fine manner, and recover exact timestamps to maintain the temporal resolution of raw data successfully. To validate the effectiveness of our method comprehensively, we perform extensive experiments on three widely used public datasets with different spatial resolutions, and additionally collect a novel event dataset covering diverse scenarios with highly dynamic motions and under harsh illumination. Besides generating high-quality dense events, our method can benefit downstream applications such as object classification and intensity frame reconstruction.

Jianing Zhang, Yuchao Zheng, Ziwei Li et al.

Gaussian splatting has gained attention for its efficient representation and rendering of 3D scenes using continuous Gaussian primitives. However, it struggles with sparse-view inputs due to limited geometric and photometric information, causing ambiguities in depth, shape, and texture. we propose GBR: Generative Bundle Refinement, a method for high-fidelity Gaussian splatting and meshing using only 4-6 input views. GBR integrates a neural bundle adjustment module to enhance geometry accuracy and a generative depth refinement module to improve geometry fidelity. More specifically, the neural bundle adjustment module integrates a foundation network to produce initial 3D point maps and point matches from unposed images, followed by bundle adjustment optimization to improve multiview consistency and point cloud accuracy. The generative depth refinement module employs a diffusion-based strategy to enhance geometric details and fidelity while preserving the scale. Finally, for Gaussian splatting optimization, we propose a multimodal loss function incorporating depth and normal consistency, geometric regularization, and pseudo-view supervision, providing robust guidance under sparse-view conditions. Experiments on widely used datasets show that GBR significantly outperforms existing methods under sparse-view inputs. Additionally, GBR demonstrates the ability to reconstruct and render large-scale real-world scenes, such as the Pavilion of Prince Teng and the Great Wall, with remarkable details using only 6 views.

Meidai Xuanyuan, Yuwang Wang, Honglei Guo et al.

In this paper, we consider a novel and practical case for talking face video generation. Specifically, we focus on the scenarios involving multi-people interactions, where the talking context, such as audience or surroundings, is present. In these situations, the video generation should take the context into consideration in order to generate video content naturally aligned with driving audios and spatially coherent to the context. 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. Inside this pipeline, we devise a 3D video diffusion model, allowing for efficient contort of both spatial conditions (landmarks and context video), as well as audio condition for temporally coherent generation. The experimental results verify the advantage of the proposed method over other baselines in terms of audio-video synchronization, video fidelity and frame consistency.

Xiaohang Yu, Haoxiang Wang, Yuqi Han et al.

This paper proposes a hybrid radiance field representation for unbounded immersive light field reconstruction which supports high-quality rendering and aggressive view extrapolation. The key idea is to first formally separate the foreground and the background and then adaptively balance learning of them during the training process. To fulfill this goal, we represent the foreground and background as two separate radiance fields with two different spatial mapping strategies. We further propose an adaptive sampling strategy and a segmentation regularizer for more clear segmentation and robust convergence. Finally, we contribute a novel immersive light field dataset, named THUImmersive, with the potential to achieve much larger space 6DoF immersive rendering effects compared with existing datasets, by capturing multiple neighboring viewpoints for the same scene, to stimulate the research and AR/VR applications in the immersive light field domain. Extensive experiments demonstrate the strong performance of our method for unbounded immersive light field reconstruction.

Tingxiong Xiao, Runzhao Yang, Yuxiao Cheng et al.

Solving partial differential equations (PDEs) has been a fundamental problem in computational science and of wide applications for both scientific and engineering research. Due to its universal approximation property, neural network is widely used to approximate the solutions of PDEs. However, existing works are incapable of solving high-order PDEs due to insufficient calculation accuracy of higher-order derivatives, and the final network is a black box without explicit explanation. To address these issues, we propose a deep learning framework to solve high-order PDEs, named SHoP. Specifically, we derive the high-order derivative rule for neural network, to get the derivatives quickly and accurately; moreover, we expand the network into a Taylor series, providing an explicit solution for the PDEs. We conduct experimental validations four high-order PDEs with different dimensions, showing that we can solve high-order PDEs efficiently and accurately.

Jinli Suo, Weihang Zhang, Jin Gong et al.

Signal capture stands in the forefront to perceive and understand the environment and thus imaging plays the pivotal role in mobile vision. Recent explosive progresses in Artificial Intelligence (AI) have shown great potential to develop advanced mobile platforms with new imaging devices. Traditional imaging systems based on the "capturing images first and processing afterwards" mechanism cannot meet this unprecedented demand. Differently, Computational Imaging (CI) systems are designed to capture high-dimensional data in an encoded manner to provide more information for mobile vision systems.Thanks to AI, CI can now be used in real systems by integrating deep learning algorithms into the mobile vision platform to achieve the closed loop of intelligent acquisition, processing and decision making, thus leading to the next revolution of mobile vision.Starting from the history of mobile vision using digital cameras, this work first introduces the advances of CI in diverse applications and then conducts a comprehensive review of current research topics combining CI and AI. Motivated by the fact that most existing studies only loosely connect CI and AI (usually using AI to improve the performance of CI and only limited works have deeply connected them), in this work, we propose a framework to deeply integrate CI and AI by using the example of self-driving vehicles with high-speed communication, edge computing and traffic planning. Finally, we outlook the future of CI plus AI by investigating new materials, brain science and new computing techniques to shed light on new directions of mobile vision systems.

Shiqi Xu, Xi Yang, Wenhui Liu et al.

Noninvasive optical imaging through dynamic scattering media has numerous important biomedical applications but still remains a challenging task. While standard diffuse imaging methods measure optical absorption or fluorescent emission, it is also well-established that the temporal correlation of scattered coherent light diffuses through tissue much like optical intensity. Few works to date, however, have aimed to experimentally measure and process such temporal correlation data to demonstrate deep-tissue video reconstruction of decorrelation dynamics. In this work, we utilize a single-photon avalanche diode (SPAD) array camera to simultaneously monitor the temporal dynamics of speckle fluctuations at the single-photon level from 12 different phantom tissue surface locations delivered via a customized fiber bundle array. We then apply a deep neural network to convert the acquired single-photon measurements into video of scattering dynamics beneath rapidly decorrelating tissue phantoms. We demonstrate the ability to reconstruct images of transient (0.1-0.4s) dynamic events occurring up to 8 mm beneath a decorrelating tissue phantom with millimeter-scale resolution, and highlight how our model can flexibly extend to monitor flow speed within buried phantom vessels.

Zhihong Zhang, Chao Deng, Yang Liu et al.

High resolution images are widely used in our daily life, whereas high-speed video capture is challenging due to the low frame rate of cameras working at the high resolution mode. Digging deeper, the main bottleneck lies in the low throughput of existing imaging systems. 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. During acquisition, multiple high-speed images are encoded and collapsed to a single measurement. After this, algorithms are employed to retrieve the video frames from the coded snapshot. Recently developed Plug-and-Play (PnP) algorithms make it possible for SCI reconstruction in large-scale problems. However, the lack of high-resolution encoding systems still precludes SCI's wide application. In this paper, we build a novel hybrid coded aperture snapshot compressive imaging (HCA-SCI) system by incorporating a dynamic liquid crystal on silicon and a high-resolution lithography mask. We further implement a PnP reconstruction algorithm with cascaded denoisers for high quality reconstruction. Based on the proposed HCA-SCI system and algorithm, we achieve a 10-mega pixel SCI system to capture high-speed scenes, leading to a high throughput of 4.6G voxels per second. Both simulation and real data experiments verify the feasibility and performance of our proposed HCA-SCI scheme.

Tao Yu, Zerong Zheng, Kaiwen Guo et al.

Human volumetric capture is a long-standing topic in computer vision and computer graphics. Although high-quality results can be achieved using sophisticated off-line systems, real-time human volumetric capture of complex scenarios, especially using light-weight setups, remains challenging. In this paper, we propose a human volumetric capture method that combines temporal volumetric fusion and deep implicit functions. To achieve high-quality and temporal-continuous reconstruction, we propose dynamic sliding fusion to fuse neighboring depth observations together with topology consistency. Moreover, for detailed and complete surface generation, we propose detail-preserving deep implicit functions for RGBD input which can not only preserve the geometric details on the depth inputs but also generate more plausible texturing results. Results and experiments show that our method outperforms existing methods in terms of view sparsity, generalization capacity, reconstruction quality, and run-time efficiency.

Yang Zheng, Ruizhi Shao, Yuxiang Zhang et al.

We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras. Our method can capture time varying surface details without the need of using pre-scanned template models. To tackle with the serious occlusion challenge for close interacting scenes, we combine a recently proposed pixel-aligned implicit function with parametric model for robust reconstruction of the invisible surface areas. An effective attention-aware module is designed to obtain the fine-grained geometry details from multi-view images, where high-fidelity results can be generated. In addition to the spatial attention method, for video inputs, we further propose a novel temporal fusion method to alleviate the noise and temporal inconsistencies for moving character reconstruction. For quantitative evaluation, we contribute a high quality multi-person dataset, MultiHuman, which consists of 150 static scenes with different levels of occlusions and ground truth 3D human models. Experimental results demonstrate the state-of-the-art performance of our method and the well generalization to real multiview video data, which outperforms the prior works by a large margin.

Xiu Li, Jinli Suo, Weihang Zhang et al.

High quality imaging usually requires bulky and expensive lenses to compensate geometric and chromatic aberrations. This poses high constraints on the optical hash or low cost applications. Although one can utilize algorithmic reconstruction to remove the artifacts of low-end lenses, the degeneration from optical aberrations is spatially varying and the computation has to trade off efficiency for performance. For example, we need to conduct patch-wise optimization or train a large set of local deep neural networks to achieve high reconstruction performance across the whole image. In this paper, we propose a PSF aware plug-and-play deep network, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating lens-specific deep priors, thus leading to a universal and flexible optical aberration correction method. Specifically, we pre-train a base model from a set of diverse lenses and then adapt it to a given lens by quickly refining the parameters, which largely alleviates the time and memory consumption of model learning. The approach is of high efficiency in both training and testing stages. Extensive results verify the promising applications of our proposed approach for compact low-end cameras.

Gaochang Wu, Yebin Liu, Lu Fang et al.

In this paper, a novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views. We indicate that the reconstruction can be efficiently modeled as angular restoration on an epipolar plane image (EPI). 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. Directly upsampling or super-resolving the light field in the angular dimensions causes ghosting effects. To suppress these ghosting effects, we contribute a novel "blur-restoration-deblur" framework. First, the "blur" step is applied to extract the low-frequency components of the light field in the spatial dimensions by convolving each EPI slice with a selected blur kernel. Then, the "restoration" step is implemented by a CNN, which is trained to restore the angular details of the EPI. Finally, we use a non-blind "deblur" operation to recover the spatial high frequencies suppressed by the EPI blur. We evaluate our approach on several datasets, including synthetic scenes, real-world scenes and challenging microscope light field data. We demonstrate the high performance and robustness of the proposed framework compared with state-of-the-art algorithms. We further show extended applications, including depth enhancement and interpolation for unstructured input. More importantly, a novel rendering approach is presented by combining the proposed framework and depth information to handle large disparities.

Xin Yuan, Yang Liu, Jinli Suo et al.

We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. 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. Exiting algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm.

Kun Li, Jinsong Zhang, Yebin Liu et al.

Human pose transfer, which aims at transferring the appearance of a given person to a target pose, is very challenging and important in many applications. Previous work ignores the guidance of pose features or only uses local attention mechanism, leading to implausible and blurry results. We propose a new human pose transfer method using a generative adversarial network (GAN) with simplified cascaded blocks. 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. We also design pre-posed image-guided pose feature update and post-posed pose-guided image feature update to better utilize the pose and image features. Our network is simple, stable, and easy to train. Quantitative and qualitative results on Market-1501 and DeepFashion datasets show the efficacy and efficiency of our model. Compared with state-of-the-art methods, our model generates sharper and more realistic images with rich details, while having fewer parameters and faster speed. Furthermore, our generated images can help to alleviate data insufficiency for person re-identification.

Zerong Zheng, Tao Yu, Qionghai Dai et al.

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. However, unlike polygon mesh-based templates, it remains a challenge to reason dense correspondences or other semantic relationships across shapes represented by DIFs, which limits its applications in texture transfer, shape analysis and so on. To overcome this limitation and also make DIFs more interpretable, we propose Deep Implicit Templates, a new 3D shape representation that supports explicit correspondence reasoning in deep implicit representations. Our key idea is to formulate DIFs as conditional deformations of a template implicit function. To this end, we propose Spatial Warping LSTM, which decomposes the conditional spatial transformation into multiple affine transformations and guarantees generalization capability. Moreover, the training loss is carefully designed in order to achieve high reconstruction accuracy while learning a plausible template with accurate correspondences in an unsupervised manner. Experiments show that our method can not only learn a common implicit template for a collection of shapes, but also establish dense correspondences across all the shapes simultaneously without any supervision.

Tiankuang Zhou, Xing Lin, Jiamin Wu et al.

Application-specific optical processors have been considered disruptive technologies for modern computing that can fundamentally accelerate the development of artificial intelligence (AI) by offering substantially improved computing performance. Recent advancements in optical neural network architectures for neural information processing have been applied to perform various machine learning tasks. However, the existing architectures have limited complexity and performance; and each of them requires its own dedicated design that cannot be reconfigured to switch between different neural network models for different applications after deployment. 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. It allocates almost all of its computational operations optically and achieves extremely high speed of data modulation and large-scale network parameter updating by dynamically programming optical modulators and photodetectors. We demonstrated the reconfiguration of the DPU to implement various diffractive feedforward and recurrent neural networks and developed a novel adaptive training approach to circumvent the system imperfections. We applied the trained networks for high-speed classifying of handwritten digit images and human action videos over benchmark datasets, and the experimental results revealed a comparable classification accuracy to the electronic computing approaches. Furthermore, our prototype system built with off-the-shelf optoelectronic components surpasses the performance of state-of-the-art graphics processing units (GPUs) by several times on computing speed and more than an order of magnitude on system energy efficiency.

Zerong Zheng, Tao Yu, Yebin Liu et al.

Modeling 3D humans accurately and robustly from a single image is very challenging, and the key for such an ill-posed problem is the 3D representation of the human models. 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. In our PaMIR-based reconstruction framework, a novel deep neural network is proposed to regularize the free-form deep implicit function using the semantic features of the parametric model, which improves the generalization ability under the scenarios of challenging poses and various clothing topologies. Moreover, a novel depth-ambiguity-aware training loss is further integrated to resolve depth ambiguities and enable successful surface detail reconstruction with imperfect body reference. Finally, we propose a body reference optimization method to improve the parametric model estimation accuracy and to enhance the consistency between the parametric model and the implicit function. With the PaMIR representation, our framework can be easily extended to multi-image input scenarios without the need of multi-camera calibration and pose synchronization. Experimental results demonstrate that our method achieves state-of-the-art performance for image-based 3D human reconstruction in the cases of challenging poses and clothing types.

Xueyang Wang, Xiya Zhang, Yinheng Zhu et al.

We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset, for large-scale, long-term, and multi-object visual analysis. The videos in PANDA were captured by a gigapixel camera and cover real-world scenes with both wide field-of-view (~1 square kilometer area) and high-resolution details (~gigapixel-level/frame). The scenes may contain 4k head counts with over 100x scale variation. PANDA provides enriched and hierarchical ground-truth annotations, including 15,974.6k bounding boxes, 111.8k fine-grained attribute labels, 12.7k trajectories, 2.2k groups and 2.9k interactions. We benchmark the human detection and tracking tasks. Due to the vast variance of pedestrian pose, scale, occlusion and trajectory, existing approaches are challenged by both accuracy and efficiency. Given the uniqueness of PANDA with both wide FoV and high resolution, a new task of interaction-aware group detection is introduced. We design a 'global-to-local zoom-in' framework, where global trajectories and local interactions are simultaneously encoded, yielding promising results. 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. PANDA Website: http://www.panda-dataset.com.

Haoqian Wang, Zhiwei Xu, Jun Xu et al.

Image recognition is an important topic in computer vision and image processing, and has been mainly addressed by supervised deep learning methods, which need a large set of labeled images to achieve promising performance. However, in most cases, labeled data are expensive or even impossible to obtain, while unlabeled data are readily available from numerous free on-line resources and have been exploited to improve the performance of deep neural networks. To better exploit the power of unlabeled data for image recognition, in this paper, we propose a semi-supervised and generative approach, namely the semi-supervised self-growing generative adversarial network (SGGAN). Label inference is a key step for the success of semi-supervised learning approaches. There are two main problems in label inference: how to measure the confidence of the unlabeled data and how to generalize the classifier. We address these two problems via the generative framework and a novel convolution-block-transformation technique, respectively. To stabilize and speed up the training process of SGGAN, we employ the metric Maximum Mean Discrepancy as the feature matching objective function and achieve larger gain than the standard semi-supervised GANs (SSGANs), narrowing the gap to the supervised methods. Experiments on several benchmark datasets show the effectiveness of the proposed SGGAN on image recognition and facial attribute recognition tasks. By using the training data with only 4% labeled facial attributes, the SGGAN approach can achieve comparable accuracy with leading supervised deep learning methods with all labeled facial attributes.

Zerong Zheng, Tao Yu, Yixuan Wei et al.

We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D human reconstruction from a single RGB image. To reduce the ambiguities associated with the surface geometry reconstruction, even for the reconstruction of invisible areas, we propose and leverage a dense semantic representation generated from SMPL model as an additional input. One key feature of our network is that it fuses different scales of image features into the 3D space through volumetric feature transformation, which helps to recover accurate surface geometry. The visible surface details are further refined through a normal refinement network, which can be concatenated with the volume generation network using our proposed volumetric normal projection layer. We also contribute THuman, a 3D real-world human model dataset containing about 7000 models. The network is trained using training data generated from the dataset. Overall, due to the specific design of our network and the diversity in our dataset, our method enables 3D human model estimation given only a single image and outperforms state-of-the-art approaches.

Tao Yu, Zerong Zheng, Yuan Zhong et al.

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. Our main contributions are: (i) a multi-layer representation of garments and body, and (ii) a physics-based performance capture procedure. We first digitize the performer using multi-layer surface representation, which includes the undressed body surface and separate clothing meshes. For performance capture, we perform skeleton tracking, cloth simulation, and iterative depth fitting sequentially for the incoming frame. By incorporating cloth simulation into the performance capture pipeline, we can simulate plausible cloth dynamics and cloth-body interactions even in the occluded regions, which was not possible in previous capture methods. Moreover, by formulating depth fitting as a physical process, our system produces cloth tracking results consistent with the depth observation while still maintaining physical constraints. Results and evaluations show the effectiveness of our method. Our method also enables new types of applications such as cloth retargeting, free-viewpoint video rendering and animations.

Xiu Li, Yebin Liu, Hanbyul Joo et al.

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture can help the collection of a high-quality dataset for training the dense pose detector. Specifically, we first introduce a novel markerless motion capture method that can take advantage of dense parsing capability provided by the dense pose detector. Thanks to the introduced dense human parsing ability, our method is demonstrated much more efficient, and accurate compared with the available state-of-the-art markerless motion capture approach. Second, we improve the performance of available dense pose detector by using multiview markerless motion capture data. Such dataset is beneficial to dense pose training because they are more dense and accurate and consistent, and can compensate for the corner cases such as unusual viewpoints. We quantitatively demonstrate the improved performance of our dense pose detector over the available DensePose. Our dense pose dataset and detector will be made public.

Yang Liu, Xin Yuan, Jinli Suo et al.

Snapshot compressive imaging (SCI) refers to compressive imaging systems where multiple frames are mapped into a single measurement, with video compressive imaging and hyperspectral compressive imaging as two representative applications. Though exciting results of high-speed videos and hyperspectral images have been demonstrated, the poor reconstruction quality precludes SCI from wide applications.This paper aims to boost the reconstruction quality of SCI via exploiting the high-dimensional structure in the desired signal. We build a joint model to integrate the nonlocal self-similarity of video/hyperspectral frames and the rank minimization approach with the SCI sensing process. Following this, an alternating minimization algorithm is developed to solve this non-convex problem. We further investigate the special structure of the sampling process in SCI to tackle the computational workload and memory issues in SCI reconstruction. Both simulation and real data (captured by four different SCI cameras) results demonstrate that our proposed algorithm leads to significant improvements compared with current state-of-the-art algorithms. We hope our results will encourage the researchers and engineers to pursue further in compressive imaging for real applications.

Tao Yu, Zerong Zheng, Kaiwen Guo et al.

We propose DoubleFusion, a new real-time system that combines volumetric dynamic reconstruction with data-driven template fitting to simultaneously reconstruct detailed geometry, non-rigid motion and the inner human body shape from a single depth camera. One of the key contributions of this method is a double layer representation consisting of a complete parametric body shape inside, and a gradually fused outer surface layer. A pre-defined node graph on the body surface parameterizes the non-rigid deformations near the body, and a free-form dynamically changing graph parameterizes the outer surface layer far from the body, which allows more general reconstruction. We further propose a joint motion tracking method based on the double layer representation to enable robust and fast motion tracking performance. Moreover, the inner body shape is optimized online and forced to fit inside the outer surface layer. Overall, our method enables increasingly denoised, detailed and complete surface reconstructions, fast motion tracking performance and plausible inner body shape reconstruction in real-time. In particular, experiments show improved fast motion tracking and loop closure performance on more challenging scenarios.

Liheng Bian, Jinli Suo, Qionghai Dai et al.

Single-pixel imaging (SPI) is a novel technique capturing 2D images using a photodiode, instead of conventional 2D array sensors. SPI owns high signal-to-noise ratio, wide spectrum range, low cost, and robustness to light scattering. Various algorithms have been proposed for SPI reconstruction, including the linear correlation methods, the alternating projection method (AP), and the compressive sensing based methods. However, there has been no comprehensive review discussing respective advantages, which is important for SPI's further applications and development. In this paper, we reviewed and compared these algorithms in a unified reconstruction framework. Besides, we proposed two other SPI algorithms including a conjugate gradient descent based method (CGD) and a Poisson maximum likelihood based method. Both simulations and experiments validate the following conclusions: to obtain comparable reconstruction accuracy, the compressive sensing based total variation regularization method (TV) requires the least measurements and consumes the least running time for small-scale reconstruction; the CGD and AP methods run fastest in large-scale cases; the TV and AP methods are the most robust to measurement noise. In a word, there are trade-offs between capture efficiency, computational complexity and robustness to noise among different SPI algorithms. We have released our source code for non-commercial use.

Lan Xu, Lu Fang, Wei Cheng et al.

Aiming at automatic, convenient and non-instrusive motion capture, this paper presents a new generation markerless motion capture technique, the FlyCap system, to capture surface motions of moving characters using multiple autonomous flying cameras (autonomous unmanned aerial vehicles(UAV) each integrated with an RGBD video camera). During data capture, three cooperative flying cameras automatically track and follow the moving target who performs large scale motions in a wide space. 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. We leverage the using of visual-odometry information provided by the UAV platform, and formulate the surface tracking problem in a non-linear objective function that can be linearized and effectively minimized through a Gaussian-Newton method. Quantitative and qualitative experimental results demonstrate the competent and plausible surface and motion reconstruction results

Liheng Bian, Jinli Suo, Jaebum Chung et al.

Fourier ptychographic microscopy (FPM) is a novel computational coherent imaging technique for high space-bandwidth product imaging. Mathematically, Fourier ptychographic (FP) reconstruction can be implemented as a phase retrieval optimization process, in which we only obtain low resolution intensity images corresponding to the sub-bands of the sample's high resolution (HR) spatial spectrum, and aim to retrieve the complex HR spectrum. In real setups, the measurements always suffer from various degenerations such as Gaussian noise, Poisson noise, speckle noise and pupil location error, which would largely degrade the reconstruction. To efficiently address these degenerations, we propose a novel FP reconstruction method under a gradient descent optimization framework in this paper. The technique utilizes Poisson maximum likelihood for better signal modeling, and truncated Wirtinger gradient for error removal. Results on both simulated data and real data captured using our laser FPM setup show that the proposed method outperforms other state-of-the-art algorithms. Also, we have released our source code for non-commercial use.

Dongsheng An, Jinli Suo, Xiangyang Ji et al.

Specular reflection exists widely in photography and causes the recorded color deviating from its true value, so fast and high quality highlight removal from a single nature image is of great importance. In spite of the progress in the past decades in highlight removal, achieving wide applicability to the large diversity of nature scenes is quite challenging. To handle this problem, we propose an analytic solution to highlight removal based on an L2 chromaticity definition and corresponding dichromatic model. 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. In the former illumination orthogonal subspace, which is specular-free, we can conduct robust clustering with an explicit criterion to determine the cluster number adaptively. In the latter illumination parallel subspace, a property called pure diffuse pixels distribution rule (PDDR) helps map each specular-influenced pixel to its diffuse component. In terms of efficiency, the proposed approach involves few complex calculation, and thus can remove highlight from high resolution images fast. Experiments show that this method is of superior performance in various challenging cases.

Zhaofei Yu, Feng Chen, Jianwu Dong et al.

Causal inference in cue combination is to decide whether the cues have a single cause or multiple causes. 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. The existing method based on calculating log posterior ratio with variable elimination has the problem of being unrealistic and task-specific. In this paper, we take advantages of the special structure of the Bayesian causal inference model and propose a hierarchical inference algorithm based on importance sampling. A simple neural circuit is designed to implement the proposed inference algorithm. Theoretical analyses and experimental results demonstrate that our algorithm converges to the accurate value as the sample size goes to infinite. Moreover, the neural circuit we design can be easily generalized to implement inference for other problems, such as the multi-stimuli cause inference and the same-different judgment.

Xuehui Wang, Jinli Suo, Jingyi Yu et al.

Coded aperture imaging systems have recently shown great success in recovering scene depth and extending the depth-of-field. The ideal pattern, however, would have to serve two conflicting purposes: 1) be broadband to ensure robust deconvolution and 2) has sufficient zero-crossings for a high depth discrepancy. This paper presents a simple but effective scene-adaptive coded aperture solution to bridge this gap. We observe that the geometric structures in a natural scene often exhibit only a few edge directions, and the successive frames are closely correlated. Therefore we adopt a spatial partitioning and temporal propagation scheme. In each frame, we address one principal direction by applying depth-discriminative codes along it and broadband codes along its orthogonal direction. Since within a frame only the regions with edge direction corresponding to its aperture code behaves well, we utilize the close among-frame correlation to propagate the high quality single frame results temporally to obtain high performance over the whole image lattice. To physically implement this scheme, we use a Liquid Crystal on Silicon (LCoS) microdisplay that permits fast changing pattern codes. Firstly, we capture the scene with a pinhole and analyze the scene content to determine primary edge orientations. Secondly, we sequentially apply the proposed coding scheme with these orientations in the following frames. Experiments on both synthetic and real scenes show that our technique is able to combine advantages of the state-of-the-art patterns for recovering better quality depth map and all-focus images.

Liheng Bian, Jinli Suo, Feng Chen et al.

Optical coherence tomography (OCT) is an important interferometric diagnostic technique which provides cross-sectional views of the subsurface microstructure of biological tissues. However, the imaging quality of high-speed OCT is limited due to the large speckle noise. To address this problem, this paper proposes a multi-frame algorithmic method to denoise OCT volume. Mathematically, we build an optimization model which forces the temporally registered frames to be low rank, and the gradient in each frame to be sparse, under logarithmic image formation and noise variance constraints. Besides, a convex optimization algorithm based on the augmented Lagrangian method is derived to solve the above model. The results reveal that our approach outperforms the other methods in terms of both speckle noise suppression and crucial detail preservation.