Image deraining is an important yet challenging image processing task. Though deterministic image deraining methods are developed with encouraging performance, they are infeasible to learn flexible representations for probabilistic inference and diverse predictions. Besides, rain intensity varies both in spatial locations and across color channels, making this task more difficult. In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image. To perform spatially adaptive deraining, we propose a spatial density estimation (SDE) module to estimate a rain density map for each image. Since rain density varies across different color channels, we also propose a channel-wise (CW) deraining scheme. Experiments on synthesized and real-world datasets show that the proposed CVID network achieves much better performance than previous deterministic methods on image deraining. Extensive ablation studies validate the effectiveness of the proposed SDE module and CW scheme in our CVID network. The code is available at \url{https://github.com/Yingjun-Du/VID}.
A deraining network can be interpreted as a conditional generator that aims at removing rain streaks from image. Most existing image deraining methods ignore model errors caused by uncertainty that reduces embedding quality. Unlike existing image deraining methods that embed low-quality features into the model directly, we replace low-quality features by latent high-quality features. The spirit of closed-loop feedback in the automatic control field is borrowed to obtain latent high-quality features. A new method for error detection and feature compensation is proposed to address model errors. …
Rethinking Real-world Image Deraining via An Unpaired Degradation-Conditioned Diffusion Model
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Science and Technology of China（中国科学技术大学）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Bosch Center for Artificial Intelligence（博世人工智能中心）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
Prediction of future states of the environment and interacting agents is a key competence required for autonomous agents to operate successfully in the real world. Prior work for structured sequence prediction based on latent variable models imposes a uni-modal standard Gaussian prior on the latent variables. This induces a strong model bias which makes it challenging to fully capture the multi-modality of the distribution of the future states. In this work, we introduce Conditional Flow Variational Autoencoders (CF-VAE) using our novel conditional normalizing flow based prior to capture compl…
Domain adaptation approaches aim to exploit useful information from the source domain where supervised learning examples are easier to obtain to address a learning problem in the target domain where there is no or limited availability of such examples. In classification problems, domain adaptation has been studied under varying supervised, unsupervised and semi-supervised conditions. However, a common situation when the labelled samples are available for a subset of target domain classes has been overlooked. In this paper, we formulate this particular domain adaptation problem within a general…
For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets. Most of current state-of-the-art focus on constructing powerful deep models to obtain better deraining results. In this paper, to further improve the deraining performance, we novelly attempt to handle the SIRR task from the perspective of training datasets by exploring a more efficient way to synthesize rainy images. Specifically, we build a full Bayesian generative model for rainy image where the rain layer is parameteri…
Conditional diffusion probabilistic models can model the distribution of natural images and can generate diverse and realistic samples based on given conditions. However, oftentimes their results can be unrealistic with observable color shifts and textures. We believe that this issue results from the divergence between the probabilistic distribution learned by the model and the distribution of natural images. The delicate conditions gradually enlarge the divergence during each sampling timestep. To address this issue, we introduce a new method that brings the predicted samples to the training …
Southeast University（东南大学）；University of Warwick（华威大学）
In this paper, we propose a novel variational generator framework for conditional GANs to catch semantic details for improving the generation quality and diversity. Traditional generators in conditional GANs simply concatenate the conditional vector with the noise as the input representation, which is directly employed for upsampling operations. However, the hidden condition information is not fully exploited, especially when the input is a class label. Therefore, we introduce a variational inference into the generator to infer the posterior of latent variable only from the conditional input, …
University of Fukui（福井大学）；Wenzhou Medical University（温州医科大学）
In this paper, we present a deep generative model based method to generate diverse human motion interpolation results. We resort to the Conditional Variational Auto-Encoder (CVAE) to learn human motion conditioned on a pair of given start and end motions, by leveraging the Recurrent Neural Network (RNN) structure for both the encoder and the decoder. Additionally, we introduce a regularization loss to further promote sample diversity. Once trained, our method is able to generate multiple plausible coherent motions by repetitively sampling from the learned latent space. Experiments on the publi…
The Chinese University of Hong Kong (CUHK)（香港中文大学（CUHK））
To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video. This paper proposes an Action Conditional Temporal Variational AutoEncoder (ACT-VAE) to improve motion prediction accuracy and capture movement diversity. ACT-VAE predicts pose sequences for an action clips from a single input image. It is implemented as a deep generative model that maintains temporal coherence according to the action category with a novel temporal modeling on latent space. Further, ACT-VAE is a general action sequence predicti…
National University of Singapore（新加坡国立大学）；Yale-NUS College（耶鲁-新加坡国立大学学院）
Most deraining works focus on rain streaks removal but they cannot deal adequately with heavy rain images. In heavy rain, streaks are strongly visible, dense rain accumulation or rain veiling effect significantly washes out the image, further scenes are relatively more blurry, etc. In this paper, we propose a novel method to address these problems. We put forth a 2-stage network: a physics-based backbone followed by a depth-guided GAN refinement. The first stage estimates the rain streaks, the transmission, and the atmospheric light governed by the underlying physics. To tease out these compon…
Australian National University（澳大利亚国立大学）；ACRV（澳大利亚机器人视觉中心）；Data61；Nankai University（南开大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）；Northwestern Polytechnical University（西北工业大学）
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection methods treat the saliency detection task as a point estimation problem, and produce a single saliency map following a deterministic learning pipeline. Inspired by the saliency data labeling process, we propose probabilistic RGB-D saliency detection network via conditional variational autoencoders to model human annotation uncertainty and generate multiple saliency maps for each input image by sampling in the late…
Imperial College London（帝国理工学院）；MRC London Institute of Medical Sciences（MRC伦敦医学科学研究所）
Accurate segmentation of heart structures imaged by cardiac MR is key for the quantitative analysis of pathology. High-resolution 3D MR sequences enable whole-heart structural imaging but are time-consuming, expensive to acquire and they often require long breath holds that are not suitable for patients. Consequently, multiplanar breath-hold 2D cine sequences are standard practice but are disadvantaged by lack of whole-heart coverage and low through-plane resolution. To address this, we propose a conditional variational autoencoder architecture able to learn a generative model of 3D high-resol…
SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition
School of Engineering Science, Simon Fraser University（西蒙菲莎大学工程科学学院）；School of Information Science and Technology, Eastern Institute of Technology（东方理工信息科学与技术学院）
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Tencent AI Lab（腾讯AI实验室）
Generating conversational gestures from speech audio is challenging due to the inherent one-to-many mapping between audio and body motions. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, resulting in plain/boring motions during inference. In order to overcome this problem, we propose a novel conditional variational autoencoder (VAE) that explicitly models one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code mainly models the strong correlati…
Shanghai Key Laboratory of Multidimensional Information Processing（上海市多维度信息处理重点实验室）；Key Laboratory of Advanced Theory and Application in Statistics & Data Science, East China Normal University（华东师范大学统计与数据科学前沿理论及应用重点实验室）
Novel view synthesis often needs the paired data from both the source and target views. This paper proposes a view translation model under cVAE-GAN framework without requiring the paired data. We design a conditional deformable module (CDM) which uses the view condition vectors as the filters to convolve the feature maps of the main branch in VAE. It generates several pairs of displacement maps to deform the features, like the 2D optical flows. The results are fed into the deformed feature based normalization module (DFNM), which scales and offsets the main branch feature, given its deformed o…
University of British Columbia（不列颠哥伦比亚大学）；Montréal Institute for Learning Algorithms（蒙特利尔学习算法研究所）；Inverted AI
We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained unconditional VAE. To train the conditional VAE, we only need to train an artifact to perform amortized inference over the unconditional VAE's latent variables given a conditioning input. We demonstrate our approach on tasks including image inpainting, for which it outperforms state-of-the-art GAN-based approaches at faithfully representing the inherent uncertainty.…
Institute of Digital Technologies, Loughborough University（拉夫堡大学数字技术研究所）
Synthesizing a realistic image from textual description is a major challenge in computer vision. Current text to image synthesis approaches falls short of producing a highresolution image that represent a text descriptor. Most existing studies rely either on Generative Adversarial Networks (GANs) or Variational Auto Encoders (VAEs). GANs has the capability to produce sharper images but lacks the diversity of outputs, whereas VAEs are good at producing a diverse range of outputs, but the images generated are often blurred. Taking into account the relative advantages of both GANs and VAEs, we pr…
Masked conditional variational autoencoders for chromosome straightening
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Engineering, Westlake University（西湖大学工学院）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院先进技术研究院）；West China Hospital, Sichuan University（四川大学华西医院）；University Medical Center Groningen, University of Groningen（格罗宁根大学格罗宁根医学中心）
Chongqing University（重庆大学）；University of Delaware（特拉华大学）
Data augmentation is a powerful technique for improving the performance of the few-shot classification task. It generates more samples as supplements, and then this task can be transformed into a common supervised learning issue for solution. However, most mainstream data augmentation based approaches only consider the single modality information, which leads to the low diversity and quality of generated features. In this paper, we present a novel multi-modal data augmentation approach named Dizygotic Conditional Variational AutoEncoder (DCVAE) for addressing the aforementioned issue. DCVAE co…
Transductive methods always outperform inductive methods in few-shot image classification scenarios. However, the existing few-shot methods contain a latent condition: the number of samples in each class is the same, which may be unrealistic. To cope with those cases where the query shots of each class are nonuniform (i.e. nonuniform few-shot learning), we propose a Task-Prior Conditional Variational Auto-Encoder model named TP-VAE, conditioned on support shots and constrained by a task-level prior regularization. Our method obtains high performance in the more challenging nonuniform few-shot …
Southern University of Science and Technology（南方科技大学）；University of Birmingham（伯明翰大学）
Pedestrian trajectory forecasting is a fundamental task in multiple utility areas, such as self-driving, autonomous robots, and surveillance systems. The future trajectory forecasting is multi-modal, influenced by physical interaction with scene contexts and intricate social interactions among pedestrians. The mainly existing literature learns representations of social interactions by deep learning networks, while the explicit interaction patterns are not utilized. Different interaction patterns, such as following or collision avoiding, will generate different trends of next movement, thus, th…
Speech Audio Generation from dynamic MRI via a Knowledge Enhanced Conditional Variational Autoencoder
Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）；School of Software Engineering, Xi'an Jiaotong University（西安交通大学软件工程学院）；Wake Forest University School of Medicine（威克森林大学医学学院）；Department of Radiology, Harvard Medical School（哈佛医学院放射科）
University of Central Florida（中佛罗里达大学）；Beihang University（北京航空航天大学）
Urban planning designs land-use configurations and can benefit building livable, sustainable, safe communities. Inspired by image generation, deep urban planning aims to leverage deep learning to generate land-use configurations. However, urban planning is a complex process. Existing studies usually ignore the need of personalized human guidance in planning, and spatial hierarchical structure in planning generation. Moreover, the lack of large-scale land-use configuration samples poses a data sparsity challenge. This paper studies a novel deep human guided urban planning method to jointly solv…
Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation. However, discrete latent spaces need to be sufficiently large to capture the complexities of real-world data, rendering downstream tasks computationally challenging. For instance, performing motion planning in a high-dimensional latent representation of the environment could be intractable. We consider the problem of sparsifying the discrete latent space of a…
We propose a novel amortized variational inference scheme for an empirical Bayes meta-learning model, where model parameters are treated as latent variables. We learn the prior distribution over model parameters conditioned on limited training data using a variational autoencoder approach. Our framework proposes sharing the same amortized inference network between the conditional prior and variational posterior distributions over the model parameters. While the posterior leverages both the labeled support and query data, the conditional prior is based only on the labeled support data. We show …
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；National University of Singapore（新加坡国立大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training. Considering the inherent conditional and label shifts, we would expect the alignment of $p(x|y)$ and $p(y)$. However, the widely used domain invariant feature learning (IFL) methods relies on aligning the marginal concept shift w.r.t. $p(x)$, which rests on an unrealistic assumption that $p(y)$ is invariant across domains. We thereby propose a novel variational Bayesian inference framework to enforce the conditiona…
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；School of Computer Science, University of Technology Sydney（悉尼科技大学计算机科学学院）
Class imbalance occurs in many real-world applications, including image classification, where the number of images in each class differs significantly. With imbalanced data, the generative adversarial networks (GANs) leans to majority class samples. The two recent methods, Balancing GAN (BAGAN) and improved BAGAN (BAGAN-GP), are proposed as an augmentation tool to handle this problem and restore the balance to the data. The former pre-trains the autoencoder weights in an unsupervised manner. However, it is unstable when the images from different categories have similar features. The latter is …
Huawei Noah’s Ark Lab, Huawei Technologies（华为诺亚方舟实验室，华为）；University College London（伦敦大学学院）
Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect the uncertainty information. In this work, we develop a novel computational framework that approximates the posterior distribution of the unknown image at each query observation. The proposed framework is very flexible: It handles implicit noise models and priors, it incorporates the data formation process (i.e., the forward operator), and the learned recon…
Cyprus University of Technology（塞浦路斯理工大学）；National and Kapodistrian University of Athens（雅典大学）；Aalborg University（奥尔堡大学）
Hidden Markov Models (HMMs) comprise a powerful generative approach for modeling sequential data and time-series in general. However, the commonly employed assumption of the dependence of the current time frame to a single or multiple immediately preceding frames is unrealistic; more complicated dynamics potentially exist in real world scenarios. This paper revisits conventional sequential modeling approaches, aiming to address the problem of capturing time-varying temporal dependency patterns. To this end, we propose a different formulation of HMMs, whereby the dependence on past frames is dy…
University of Padova（帕多瓦大学）；National University of Defense Technology（国防科技大学）
In open set recognition, a classifier has to detect unknown classes that are not known at training time. In order to recognize new categories, the classifier has to project the input samples of known classes in very compact and separated regions of the features space for discriminating samples of unknown classes. Recently proposed Capsule Networks have shown to outperform alternatives in many fields, particularly in image recognition, however they have not been fully applied yet to open-set recognition. In capsule networks, scalar neurons are replaced by capsule vectors or matrices, whose entr…
Pontifical Catholic University of Rio de Janeiro（里约热内卢天主教大学）
Non-Intrusive Load Monitoring (NILM) is a computational technique to estimate the power loads' appliance-by-appliance from the whole consumption measured by a single meter. In this paper, we propose a conditional density estimation model, based on deep neural networks, that joins a Conditional Variational Autoencoder with a Conditional Invertible Normalizing Flow model to estimate the individual appliance's power demand. The resulting model is called Prior Flow Variational Autoencoder or, for simplicity PFVAE. Thus, instead of having one model per appliance, the resulting model is responsible …
