CVPR 2018 论文列表

In this paper, we propose a method to solve the image restoration problem, which tries to restore the details of a corrupted image, especially due to the loss caused by JPEG compression. We have treated an image in the frequency domain to explicitly restore the frequency components lost during image compression. In doing so, the distribution in the frequency domain is learned using the cross entropy loss. Unlike recent approaches, we have reconstructed the details of an image without using the scheme of adversarial training. Rather, the image restoration problem is treated as a classification problem to determine the frequency coefficient for each frequency band in an image patch. In this paper, we show that the proposed method effectively restores a JPEG-compressed image with more detailed high frequency components, making the restored image more vivid.

To truly understand the visual world our models should be able not only to recognize images but also generate them. To this end, there has been exciting recent progress on gen- erating images from natural language descriptions. These methods give stunning results on limited domains such as descriptions of birds or flowers, but struggle to faithfully reproduce complex sentences with many objects and rela- tionships. To overcome this limitation we propose a method for generating images from scene graphs, enabling explic- itly reasoning about objects and their relationships. Our model uses graph convolution to process input graphs, com- putes a scene layout by predicting bounding boxes and seg- mentation masks for objects, and converts the layout to an image with a cascaded refinement network. The network is trained adversarially against a pair of discriminators to en- sure realistic outputs. We validate our approach on Visual Genome and COCO-Stuff, where qualitative results, abla- tions, and user studies demonstrate our method’s ability to generate complex images with multiple objects.

Image correction aims to adjust an input image into a visually pleasing one with the detail in the under/over exposed regions recovered. However, existing image correction methods are mainly based on image pixel operations, and attempting to recover the lost detail from these under/over exposed regions is challenging. We, therefore, revisit the image formation procedure and notice that detail is contained in the high dynamic range (HDR) light intensities(which can be perceived by human eyes) but is lost during the nonlinear imaging process by of the camera in the low dynamic range (LDR) domain. Inspired by this observation, we formulate the image correction problem as the Deep Reciprocating HDR Transformation (DRHT) process and propose a novel approach to first reconstruct the lost detail in the HDR domain and then transfer them back to the LDR image as the output image with the recovered detail preserved. To this end, we propose an end-to-end DRHT model, which contains two CNNs, one for HDR detail reconstruction and the other for LDR detail correction. Experiments on the standard benchmarks demonstrate the effectiveness of the proposed method, compared with state-of-the-art image correction methods.

This paper introduces an approach to simultaneously estimate 3D shape, camera pose, and object and type of deformation clustering, from partial 2D annotations in a multi-instance collection of images. Furthermore, we can indistinctly process rigid and non-rigid categories. This advances existing work, which only addresses the problem for one single object or, if multiple objects are considered, they are assumed to be clustered a priori. To handle this broader version of the problem, we model object deformation using a formulation based on multiple unions of subspaces, able to span from small rigid motion to complex deformations. The parameters of this model are learned via Augmented Lagrange Multipliers, in a completely unsupervised manner that does not require any training data at all. Extensive validation is provided in a wide variety of synthetic and real scenarios, including rigid and non-rigid categories with small and large deformations. In all cases our approach outperforms state-of-the-art in terms of 3D reconstruction accuracy, while also providing clustering results that allow segmenting the images into object instances and their associated type of deformation (or action the object is performing).

In this paper, we consider a typical image blind denoising problem, which is to remove unknown noise from noisy images. As we all know, discriminative learning based methods, such as DnCNN, can achieve state-of-the-art denoising results, but they are not applicable to this problem due to the lack of paired training data. To tackle the barrier, we propose a novel two-step framework. First, a Generative Adversarial Network (GAN) is trained to estimate the noise distribution over the input noisy images and to generate noise samples. Second, the noise patches sampled from the first step are utilized to construct a paired training dataset, which is used, in turn, to train a deep Convolutional Neural Network (CNN) for denoising. Extensive experiments have been done to demonstrate the superiority of our approach in image blind denoising.

We propose to recover 3D shape structures from single RGB images, where structure refers to shape parts represented by cuboids and part relations encompassing connectivity and symmetry. Given a single 2D image with an object depicted, our goal is automatically recover a cuboid structure of the object parts as well as their mutual relations. We develop a convolutional-recursive auto-encoder comprised of structure parsing of a 2D image followed by structure recovering of a cuboid hierarchy. The encoder is achieved by a multi-scale convolutional network trained with the task of shape contour estimation, thereby learning to discern object structures in various forms and scales. The decoder fuses the features of the structure parsing network and the original image, and recursively decodes a hierarchy of cuboids. Since the decoder network is learned to recover part relations including connectivity and symmetry explicitly, the plausibility and generality of part structure recovery can be ensured. The two networks are jointly trained using the training data of contour-mask and cuboid-structure pairs. Such pairs are generated by rendering stock 3D CAD models coming with part segmentation. Our method achieves unprecedentedly faithful and detailed recovery of diverse 3D part structures from single-view 2D images. We demonstrate two applications of our method including structure-guided completion of 3D volumes reconstructed from single-view images and structure-aware interactive editing of 2D images.

We present Im2Pano3D, a convolutional neural network that generates a dense prediction of 3D structure and a probability distribution of semantic labels for a full 360 panoramic view of an indoor scene when given only a partial observation ( <=50%) in the form of an RGB-D image. To make this possible, Im2Pano3D leverages strong contextual priors learned from large-scale synthetic and real-world indoor scenes. To ease the prediction of 3D structure, we propose to parameterize 3D surfaces with their plane equations and train the model to predict these parameters directly. To provide meaningful training supervision, we make use of multiple loss functions that consider both pixel level accuracy and global context consistency. Experiments demonstrate that Im2Pano3D is able to predict the semantics and 3D structure of the unobserved scene with more than 56% pixel accuracy and less than 0.52m average distance error, which is significantly better than alternative approaches.

Existing methods to recognize actions in static images take the images at their face value, learning the appearances---objects, scenes, and body poses---that distinguish each action class. However, such models are deprived of the rich dynamic structure and motions that also define human activity. We propose an approach that hallucinates the unobserved future motion implied by a single snapshot to help static-image action recognition. The key idea is to learn a prior over short-term dynamics from thousands of unlabeled videos, infer the anticipated optical flow on novel static images, and then train discriminative models that exploit both streams of information. Our main contributions are twofold. First, we devise an encoder-decoder convolutional neural network and a novel optical flow encoding that can translate a static image into an accurate flow map. Second, we show the power of hallucinated flow for recognition, successfully transferring the learned motion into a standard two-stream network for activity recognition. On seven datasets, we demonstrate the power of the approach. It not only achieves state-of-the-art accuracy for dense optical flow prediction, but also consistently enhances recognition of actions and dynamic scenes.

Real-world lighting often consists of multiple illuminants with different spectra. Separating and manipulating these illuminants in post-process is a challenging problem that requires either significant manual input or calibrated scene geometry and lighting. In this work, we leverage a flash/no-flash image pair to analyze and edit scene illuminants based on their spectral differences. We derive a novel physics-based relationship between color variations in the observed flash/no-flash intensities and the spectra and surface shading corresponding to individual scene illuminants. Our technique uses this constraint to automatically separate an image into constituent images lit by each illuminant. This separation can be used to support applications like white balancing, lighting editing, and RGB photometric stereo, where we demonstrate results that outperform state-of-the-art techniques on a wide range of images.

We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair. Since the answers are less informative than the questions, and the questions have less learnable bias, an iVQA model needs to better understand the image to be successful than a VQA model. We pose question generation as a multi-modal dynamic inference process and propose an iVQA model that can gradually adjust its focus of attention guided by both a partially generated question and the answer. For evaluation, apart from existing linguistic metrics, we propose a new ranking metric. This metric compares the ground truth question's rank among a list of distractors, which allows the drawbacks of different algorithms and sources of error to be studied. Experimental results show that our model can generate diverse, grammatically correct and content correlated questions that match the given answer.

With the aim of developing a fast yet accurate algorithm for compressive sensing (CS) reconstruction of natural images, we combine in this paper the merits of two existing categories of CS methods: the structure insights of traditional optimization-based methods and the performance/speed of recent network-based ones. Specifically, we propose a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general L1 norm CS reconstruction model. To cast ISTA into deep network form, we develop an effective strategy to solve the proximal mapping associated with the sparsity-inducing regularizer using nonlinear transforms. All the parameters in ISTA-Net (e.g. nonlinear transforms, shrinkage thresholds, step sizes, etc.) are learned end-to-end, rather than being hand-crafted. Moreover, considering that the residuals of natural images are more compressible, an enhanced version of ISTA-Net in the residual domain, dubbed ISTA-Net+, is derived to further improve CS reconstruction. Extensive CS experiments demonstrate that the proposed ISTA-Nets outperform existing state-of-the-art optimization-based and network-based CS methods by large margins, while maintaining fast computational speed.

We introduce Interactive Question Answering (IQA), the task of answering questions that require an autonomous agent to interact with a dynamic visual environment. IQA presents the agent with a scene and a question, like: “Are there any apples in the fridge?” The agent must navigate around the scene, acquire visual understanding of scene elements, interact with objects (e.g. open refrigerators) and plan for a series of actions conditioned on the question. Popular reinforcement learning approaches with a single controller perform poorly on IQA owing to the large and diverse state space. We propose the Hierarchical Interactive Memory Network (HIMN), consisting of a factorized set of controllers, allowing the system to operate at multiple levels of temporal abstraction. To evaluate HIMN, we introduce IQUAD V1, a new dataset built upon AI2-THOR [35], a simulated photo-realistic environment of configurable indoor scenes with interactive objects. IQUAD V1 has 75,000 questions, each paired with a unique scene configuration. Our experiments show that our proposed model outperforms popular single controller based methods on IQUAD V1. For sample questions and results, please view our video: https://youtu.be/pXd3C-1jr98.

Modern visual-inertial SLAM (VI-SLAM) achieves higher accuracy and robustness than pure visual SLAM, thanks to the complementariness of visual features and inertial measurements. However, jointly using visual and inertial measurements to optimize SLAM objective functions is a problem of high computational complexity. In many VI-SLAM applications, the conventional optimization solvers can only use a very limited number of recent measurements for real time pose estimation, at the cost of suboptimal localization accuracy. In this work, we renovate the numerical solver for VI-SLAM. Compared to conventional solvers, our proposal provides an exact solution with significantly higher computational efficiency. Our solver allows us to use remarkably larger number of measurements to achieve higher accuracy and robustness. Furthermore, our method resolves the global consistency problem that is unaddressed by many state-of-the-art SLAM systems: to guarantee the minimization of re-projection function and inertial constraint function during loop closure. Experiments demonstrate our novel formulation renders lower localization error and more than 10x speedup compared to alternatives. We release the source code of our implementation to benefit the community.

Hyperparameters are numerical presets whose values are assigned prior to the commencement of the learning process. Selecting appropriate hyperparameters is critical for the accuracy of tracking algorithms, yet it is difficult to determine their optimal values, in particular, adaptive ones for each specific video sequence. Most hyperparameter optimization algorithms depend on searching a generic range and they are imposed blindly on all sequences. Here, we propose a novel hyperparameter optimization method that can find optimal hyperparameters for a given sequence using an action-prediction network leveraged on Continuous Deep Q-Learning. Since the common state-spaces for object tracking tasks are significantly more complex than the ones in traditional control problems, existing Continuous Deep Q-Learning algorithms cannot be directly applied. To overcome this challenge, we introduce an efficient heuristic to accelerate the convergence behavior. We evaluate our method on several tracking benchmarks and demonstrate its superior performance.

There is growing interest in improving the design of deep network architectures to be both accurate and low cost. This paper explores semantic specialization as a mechanism for improving the computational efficiency (accuracy-per-unit-cost) of inference in the context of image classification. Specifically, we propose a network architecture template called HydraNet, which enables state-of-the-art architectures for image classification to be transformed into dynamic architectures which exploit conditional execution for efficient inference. HydraNets are wide networks containing distinct components specialized to compute features for visually similar classes, but they retain efficiency by dynamically selecting only a small number of components to evaluate for any one input image. This design is made possible by a soft gating mechanism that encourages component specialization during training and accurately performs component selection during inference. We evaluate the HydraNet approach on both the CIFAR-100 and ImageNet classification tasks. On CIFAR, applying the HydraNet template to the ResNet and DenseNet family of models reduces inference cost by 2-4x while retaining the accuracy of the baseline architectures. On ImageNet, applying the HydraNet template improves accuracy up to 2.5% when compared to an efficient baseline architecture with similar inference cost.

In this paper, we aim to solve the pose estimation problem of calibrated pinhole and generalized cameras w.r.t. a Structure-from-Motion (SfM) model by leveraging both 2D-3D correspondences as well as 2D-2D correspondences. Traditional approaches either focus on the use of 2D-3D matches, known as structure-based pose estimation or solely on 2D-2D matches (structure-less pose estimation). Absolute pose approaches are limited in their performance by the quality of the 3D point triangulations as well as the completeness of the 3D model. Relative pose approaches, on the other hand, while being more accurate, also tend to be far more computationally costly and often return dozens of possible solutions. This work aims to bridge the gap between these two paradigms. We propose a new RANSAC-based approach that automatically chooses the best type of solver to use at each iteration in a data-driven way. The solvers chosen by our RANSAC can range from pure structure-based or structure-less solvers, to any possible combination of hybrid solvers (i.e. using both types of matches) in between. A number of these new hybrid minimal solvers are also presented in this paper. Both synthetic and real data experiments show our approach to be as accurate as structure-less approaches, while staying close to the efficiency of structure-based methods.

We present a human-centric method to sample and synthesize 3D room layouts and 2D images thereof, for the purpose of obtaining large-scale 2D/3D image data with the perfect per-pixel ground truth. An attributed spatial And-Or graph (S-AOG) is proposed to represent indoor scenes. The S-AOG is a probabilistic grammar model, in which the terminal nodes are object entities including room, furniture, and supported objects. Human contexts as contextual relations are encoded by Markov Random Fields (MRF) on the terminal nodes. We learn the distributions from an indoor scene dataset and sample new layouts using Monte Carlo Markov Chain. Experiments demonstrate that the proposed method can robustly sample a large variety of realistic room layouts based on three criteria: (i) visual realism comparing to a state-of-the-art room arrangement method, (ii) accuracy of the affordance maps with respect to ground-truth, and (ii) the functionality and naturalness of synthesized rooms evaluated by human subjects.

Person re-identification is a challenging task mainly due to factors such as background clutter, pose, illumination and camera point of view variations. These elements hinder the process of extracting robust and discriminative representations, hence preventing different identities from being successfully distinguished. To improve the representation learning, usually local features from human body parts are extracted. However, the common practice for such a process has been based on bounding box part detection. In this paper, we propose to adopt human semantic parsing which, due to its pixel-level accuracy and capability of modeling arbitrary contours, is naturally a better alternative. Our proposed SPReID integrates human semantic parsing in person re-identification and not only considerably outperforms its counter baseline, but achieves state-of-the-art performance. We also show that, by employing a simple yet effective training strategy, standard popular deep convolutional architectures such as Inception-V3 and ResNet-152, with no modification, while operating solely on full image, can dramatically outperform current state-of-the-art. Our proposed methods improve state-of-the-art person re-identification on: Market-1501 by ~17% in mAP and ~6% in rank-1, CUHK03 by ~4% in rank-1 and DukeMTMC-reID by ~24% in mAP and ~10% in rank-1.

Human pose estimation still faces various difficulties in challenging scenarios. Human parsing, as a closely related task, can provide valuable cues for better pose estimation, which however has not been fully exploited. In this paper, we propose a novel Parsing Induced Learner to exploit parsing information to effectively assist pose estimation by learning to fast adapt the base pose estimation model. The proposed Parsing Induced Learner is composed of a parsing encoder and a pose model parameter adapter, which together learn to predict dynamic parameters of the pose model to extract complementary useful features for more accurate pose estimation. Comprehensive experiments on benchmarks LIP and extended PASCAL-Person-Part show that the proposed Parsing Induced Learner can improve performance of both single- and multi-person pose estimation to new state-of-the-art. Cross-dataset experiments also show that the proposed Parsing Induced Learner from LIP dataset can accelerate learning of a human pose estimation model on MPII benchmark in addition to achieving outperforming performance.