CVPR 2019 论文列表

Graphics Interchange Format (GIF) is a highly portable graphics format that is ubiquitous on the Internet. Despite their small sizes, GIF images often contain undesirable visual artifacts such as flat color regions, false contours, color shift, and dotted patterns. In this paper, we propose GIF2Video, the first learning-based method for enhancing the visual quality of GIFs in the wild. We focus on the challenging task of GIF restoration by recovering information lost in the three steps of GIF creation: frame sampling, color quantization, and color dithering. We first propose a novel CNN architecture for color dequantization. It is built upon a compositional architecture for multi-step color correction, with a comprehensive loss function designed to handle large quantization errors. We then adapt the SuperSlomo network for temporal interpolation of GIF frames. We introduce two large datasets, namely GIF-Faces and GIF-Moments, for both training and evaluation. Experimental results show that our method can significantly improve the visual quality of GIFs, and outperforms direct baseline and state-of-the-art approaches.

To bridge source and target domains for domain adaptation, there are three important types of information including data structure, domain label, and class label. Most existing domain adaptation approaches exploit only one or two types of this information and cannot make them complement and enhance each other. Different from existing methods, we propose an end-to-end Graph Convolutional Adversarial Network (GCAN) for unsupervised domain adaptation by jointly modeling data structure, domain label, and class label in a unified deep framework. The proposed GCAN model enjoys several merits. First, to the best of our knowledge, this is the first work to model the three kinds of information jointly in a deep model for unsupervised domain adaptation. Second, the proposed model has designed three effective alignment mechanisms including structure-aware alignment, domain alignment, and class centroid alignment, which can learn domain-invariant and semantic representations effectively to reduce the domain discrepancy for domain adaptation. Extensive experimental results on five standard benchmarks demonstrate that the proposed GCAN algorithm performs favorably against state-of-the-art unsupervised domain adaptation methods.

In the past few years, a lot of work has been done towards reconstructing the 3D facial structure from single images by capitalizing on the power of Deep Convolutional Neural Networks (DCNNs). In the most recent works, differentiable renderers were employed in order to learn the relationship between the facial identity features and the parameters of a 3D morphable model for shape and texture. The texture features either correspond to components of a linear texture space or are learned by auto-encoders directly from in-the-wild images. In all cases, the quality of the facial texture reconstruction of the state-of-the-art methods is still not capable of modeling textures in high fidelity. In this paper, we take a radically different approach and harness the power of Generative Adversarial Networks (GANs) and DCNNs in order to reconstruct the facial texture and shape from single images. That is, we utilize GANs to train a very powerful generator of facial texture in UV space. Then, we revisit the original 3D Morphable Models (3DMMs) fitting approaches making use of non-linear optimization to find the optimal latent parameters that best reconstruct the test image but under a new perspective. We optimize the parameters with the supervision of pretrained deep identity features through our end-to-end differentiable framework. We demonstrate excellent results in photorealistic and identity preserving 3D face reconstructions and achieve for the first time, to the best of our knowledge, facial texture reconstruction with high-frequency details.

Efficient neural network inference is important in a number of practical domains, such as deployment in mobile settings. An effective method for increasing inference efficiency is to use low bitwidth arithmetic, which can subsequently be accelerated using dedicated hardware. However, designing effective quantization schemes while maintaining network accuracy is challenging. In particular, current techniques face difficulty in performing fully end-to-end quantization, making use of aggressively low bitwidth regimes such as 4-bit, and applying quantized networks to complex tasks such as object detection. In this paper, we demonstrate that many of these difficulties arise because of instability during the fine-tuning stage of the quantization process, and propose several novel techniques to overcome these instabilities. We apply our techniques to produce fully quantized 4-bit detectors based on RetinaNet and Faster R-CNN, and show that these achieve state-of-the-art performance for quantized detectors. The mAP loss due to quantization using our methods is more than 3.8x less than the loss from existing methods.

Benefitted from its great success on many tasks, deep learning is increasingly used on low-computational-cost devices, e.g. smartphone, embedded devices, etc. To reduce the high computational and memory cost, in this work, we propose a fully learnable group convolution module (FLGC for short) which is quite efficient and can be embedded into any deep neural networks for acceleration. Specifically, our proposed method automatically learns the group structure in the training stage in a fully end-to-end manner, leading to a better structure than the existing pre-defined, two-steps, or iterative strategies. Moreover, our method can be further combined with depthwise separable convolution, resulting in 5 times acceleration than the vanilla Resnet50 on single CPU. An additional advantage is that in our FLGC the number of groups can be set as any value, but not necessarily 2^k as in most existing methods, meaning better tradeoff between accuracy and speed. As evaluated in our experiments, our method achieves better performance than existing learnable group convolution and standard group convolution when using the same number of groups.

We present a fully automatic approach to video colorization with self-regularization and diversity. Our model contains a colorization network for video frame colorization and a refinement network for spatiotemporal color refinement. Without any labeled data, both networks can be trained with self-regularized losses defined in bilateral and temporal space. The bilateral loss enforces color consistency between neighboring pixels in a bilateral space and the temporal loss imposes constraints between corresponding pixels in two nearby frames. While video colorization is a multi-modal problem, our method uses a perceptual loss with diversity to differentiate various modes in the solution space. Perceptual experiments demonstrate that our approach outperforms state-of-the-art approaches on fully automatic video colorization.

Robust and accurate visual localization is a fundamental capability for numerous applications, such as autonomous driving, mobile robotics, or augmented reality. It remains, however, a challenging task, particularly for large-scale environments and in presence of significant appearance changes. State-of-the-art methods not only struggle with such scenarios, but are often too resource intensive for certain real-time applications. In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization. We exploit the coarse-to-fine localization paradigm: we first perform a global retrieval to obtain location hypotheses and only later match local features within those candidate places. This hierarchical approach incurs significant runtime savings and makes our system suitable for real-time operation. By leveraging learned descriptors, our method achieves remarkable localization robustness across large variations of appearance and sets a new state-of-the-art on two challenging benchmarks for large-scale localization.

In this paper, we address the problem of rain removal from videos by proposing a more comprehensive framework that considers the additional degradation factors in real scenes neglected in previous works. The proposed framework is built upon a two-stage recurrent network with dual-level flow regularizations to perform the inverse recovery process of the rain synthesis model for video deraining. The rain-free frame is estimated from the single rain frame at the first stage. It is then taken as guidance along with previously recovered clean frames to help obtain a more accurate clean frame at the second stage. This two-step architecture is capable of extracting more reliable motion information from the initially estimated rain-free frame at the first stage for better frame alignment and motion modeling at the second stage. Furthermore, to keep the motion consistency between frames that facilitates a frame-consistent deraining model at the second stage, a dual-level flow based regularization is proposed at both coarse flow and fine pixel levels. To better train and evaluate the proposed video deraining network, a novel rain synthesis model is developed to produce more visually authentic paired training and evaluation videos. Extensive experiments on a series of synthetic and real videos verify not only the superiority of the proposed method over state-of-the-art but also the effectiveness of network design and its each component.

Existing image inpainting methods typically fill holes by borrowing information from surrounding pixels. They often produce unsatisfactory results when the holes overlap with or touch foreground objects due to lack of information about the actual extent of foreground and background regions within the holes. These scenarios, however, are very important in practice, especially for applications such as distracting object removal. To address the problem, we propose a foreground-aware image inpainting system that explicitly disentangles structure inference and content completion. Specifically, our model learns to predict the foreground contour first, and then inpaints the missing region using the predicted contour as guidance. We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting. Experiments show that our method significantly outperforms existing methods and achieves superior inpainting results on challenging cases with complex compositions.

Event cameras are novel vision sensors that output pixel-level brightness changes ("events") instead of traditional video frames. These asynchronous sensors offer several advantages over traditional cameras, such as, high temporal resolution, very high dynamic range, and no motion blur. To unlock the potential of such sensors, motion compensation methods have been recently proposed. We present a collection and taxonomy of twenty two objective functions to analyze event alignment in motion compensation approaches. We call them focus loss functions since they have strong connections with functions used in traditional shape-from-focus applications. The proposed loss functions allow bringing mature computer vision tools to the realm of event cameras. We compare the accuracy and runtime performance of all loss functions on a publicly available dataset, and conclude that the variance, the gradient and the Laplacian magnitudes are among the best loss functions. The applicability of the loss functions is shown on multiple tasks: rotational motion, depth and optical flow estimation. The proposed focus loss functions allow to unlock the outstanding properties of event cameras.

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few try to estimate scene flow directly from point clouds. In this work, we propose a novel deep neural network named FlowNet3D that learns scene flow from point clouds in an end-to-end fashion. Our network simultaneously learns deep hierarchical features of point clouds and flow embeddings that represent point motions, supported by two newly proposed learning layers for point sets. We evaluate the network on both challenging synthetic data from FlyingThings3D and real Lidar scans from KITTI. Trained on synthetic data only, our network successfully generalizes to real scans, outperforming various baselines and showing competitive results to the prior art. We also demonstrate two applications of our scene flow output (scan registration and motion segmentation) to show its potential wide use cases.

This paper addresses the problem of multiple models fitting in the general context where the sought structures can be described by a mixture of heterogeneous parametric models drawn from different classes. To this end, we conceive a multi-model selection framework that extend T-linkage to cope with different nested class of models. Our method, called MCT, compares favourably with the state-of-the-art on publicly available data-sets for various fitting problems: lines and conics, homographies and fundamental matrices, planes and cylinders.

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations. Most methods based on image-level annotations use localization maps obtained from the classifier, but these only focus on the small discriminative parts of objects and do not capture precise boundaries. FickleNet explores diverse combinations of locations on feature maps created by generic deep neural networks. It selects hidden units randomly and then uses them to obtain activation scores for image classification. FickleNet implicitly learns the coherence of each location in the feature maps, resulting in a localization map which identifies both discriminative and other parts of objects. The ensemble effects are obtained from a single network by selecting random hidden unit pairs, which means that a variety of localization maps are generated from a single image. Our approach does not require any additional training steps and only adds a simple layer to a standard convolutional neural network; nevertheless it outperforms recent comparable techniques on the Pascal VOC 2012 benchmark in both weakly and semi-supervised settings.

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) generating or hallucinating additional data from the limited existing samples. In this paper, we follow the latter direction and present a novel data hallucination model. Currently, most datapoint generators contain a specialized network (i.e., GAN) tasked with hallucinating new datapoints, thus requiring large numbers of annotated data for their training in the first place. In this paper, we propose a novel less-costly hallucination method for few-shot learning which utilizes saliency maps. To this end, we employ a saliency network to obtain the foregrounds and backgrounds of available image samples and feed the resulting maps into a two-stream network to hallucinate datapoints directly in the feature space from viable foreground-background combinations. To the best of our knowledge, we are the first to leverage saliency maps for such a task and we demonstrate their usefulness in hallucinating additional datapoints for few-shot learning. Our proposed network achieves the state of the art on publicly available datasets.

To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe several significant challenges. First, the target domain data is highly insufficient, making most existing domain adaptation methods ineffective. Second, object detection involves simultaneous localization and classification, further complicating the model adaptation process. Third, the model suffers from over-adaptation (similar to overfitting when training with a few data example) and instability risk that may lead to degraded detection performance in the target domain. To address these challenges, we first introduce a pairing mechanism over source and target features to alleviate the issue of insufficient target domain samples. We then propose a bi-level module to adapt the source trained detector to the target domain: 1) the split pooling based image level adaptation module uniformly extracts and aligns paired local patch features over locations, with different scale and aspect ratio; 2) the instance level adaptation module semantically aligns paired object features while avoids inter-class confusion. Meanwhile, a source model feature regularization (SMFR) is applied to stabilize the adaptation process of the two modules. Combining these contributions gives a novel few-shot adaptive Faster-RCNN framework, termed FAFRCNN, which effectively adapts to target domain with a few labeled samples. Experiments with multiple datasets show that our model achieves new state-of-the-art performance under both the interested few-shot domain adaptation(FDA) and unsupervised domain adaptation(UDA) setting.

Recent advances in image super-resolution (SR) explored the power of deep learning to achieve a better reconstruction performance. However, the feedback mechanism, which commonly exists in human visual system, has not been fully exploited in existing deep learning based image SR methods. In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information. Specifically, we use hidden states in a recurrent neural network (RNN) with constraints to achieve such feedback manner. A feedback block is designed to handle the feedback connections and to generate powerful high-level representations. The proposed SRFBN comes with a strong early reconstruction ability and can create the final high-resolution image step by step. In addition, we introduce a curriculum learning strategy to make the network well suitable for more complicated tasks, where the low-resolution images are corrupted by multiple types of degradation. Extensive experimental results demonstrate the superiority of the proposed SRFBN in comparison with the state-of-the-art methods. Code is avaliable at https://github.com/Paper99/SRFBN_CVPR19.

We propose feedback adversarial learning (FAL) framework that can improve existing generative adversarial networks by leveraging spatial feedback from the discriminator. We formulate the generation task as a recurrent framework, in which the discriminator's feedback is integrated into the feedforward path of the generation process. Specifically, the generator conditions on the discriminator's spatial output response, and its previous generation to improve generation quality over time - allowing the generator to attend and fix its previous mistakes. To effectively utilize the feedback, we propose an adaptive spatial transform layer, which learns to spatially modulate feature maps from its previous generation and the error signal from the discriminator. We demonstrate that one can easily adapt FAL to existing adversarial learning frameworks on a wide range of tasks, including image generation, image-to-image translation, and voxel generation.

Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization remains an open issue. We systematically summarize the detrimental factors as task-relevant/irrelevant semantic variations and unspecified latent variation. In this paper, we cast these problems as an adversarial minimax game in the latent space. Specifically, we propose equipping an end-to-end conditional adversarial network with the ability to decompose an input sample into three complementary parts. The discriminative representation inherits the desired invariance property guided by prior knowledge of the task, which is marginally independent to the task-relevant/irrelevant semantic and latent variations. Our proposed framework achieves top performance on a serial of tasks, including digits recognition, lighting, makeup, disguise-tolerant face recognition, and facial attributes recognition.

Despite the large volume of face recognition datasets, there is a significant portion of subjects, of which the samples are insufficient and thus under-represented. Ignoring such significant portion results in insufficient training data. Training with under-represented data leads to biased classifiers in conventionally-trained deep networks. In this paper, we propose a center-based feature transfer framework to augment the feature space of under-represented subjects from the regular subjects that have sufficiently diverse samples. A Gaussian prior of the variance is assumed across all subjects and the variance from regular ones are transferred to the under-represented ones. This encourages the under-represented distribution to be closer to the regular distribution. Further, an alternating training regimen is proposed to simultaneously achieve less biased classifiers and a more discriminative feature representation. We conduct ablative study to mimic the under-represented datasets by varying the portion of under-represented classes on the MS-Celeb-1M dataset. Advantageous results on LFW, IJB-A and MS-Celeb-1M demonstrate the effectiveness of our feature transfer and training strategy, compared to both general baselines and state-of-the-art methods. Moreover, our feature transfer successfully presents smooth visual interpolation, which conducts disentanglement to preserve identity of a class while augmenting its feature space with non-identity variations such as pose and lighting.