CVPR 2018 论文列表

Popular research areas like autonomous driving and augmented reality have renewed the interest in image-based camera localization. In this work, we address the task of predicting the 6D camera pose from a single RGB image in a given 3D environment. With the advent of neural networks, previous works have either learned the entire camera localization process, or multiple components of a camera localization pipeline. Our key contribution is to demonstrate and explain that learning a single component of this pipeline is sufficient. This component is a fully convolutional neural network for densely regressing so-called scene coordinates, defining the correspondence between the input image and the 3D scene space. The neural network is prepended to a new end-to-end trainable pipeline. Our system is efficient, highly accurate, robust in training, and exhibits outstanding generalization capabilities. It exceeds state-of-the-art consistently on indoor and outdoor datasets. Interestingly, our approach surpasses existing techniques even without utilizing a 3D model of the scene during training, since the network is able to discover 3D scene geometry automatically, solely from single-view constraints.

In this paper, we introduce the concept of learning latent super-events from activity videos, and present how it benefits activity detection in continuous videos. We define a super-event as a set of multiple events occurring together in videos with a particular temporal organization; it is the opposite concept of sub-events. Real-world videos contain multiple activities and are rarely segmented (e.g., surveillance videos), and learning latent super-events allows the model to capture how the events are temporally related in videos. We design emph{temporal structure filters} that enable the model to focus on particular sub-intervals of the videos, and use them together with a soft attention mechanism to learn representations of latent super-events. Super-event representations are combined with per-frame or per-segment CNNs to provide frame-level annotations. Our approach is designed to be fully differentiable, enabling end-to-end learning of latent super-event representations jointly with the activity detector using them. Our experiments with multiple public video datasets confirm that the proposed concept of latent super-event learning significantly benefits activity detection, advancing the state-of-the-arts.

Single-view intrinsic image decomposition is a highly ill-posed problem, making learning from large amounts of data an attractive approach. However, it is difficult to collect ground truth training data at scale for intrinsic images. In this paper, we explore a different approach to learning intrinsic images: observing image sequences over time depicting the same scene under changing illumination, and learning single-view decompositions that are consistent with these changes. This approach allows us to learn without ground truth decompositions, and instead to exploit information available from multiple images. Our trained model can then be applied at test time to single views. We describe a new learning framework based on this idea, including new loss functions that can be efficiently evaluated over entire sequences. While prior learning-based intrinsic image methods achieve good performance on specific benchmarks, we show that our approach generalizes well to several diverse datasets, including MIT intrinsic images, Intrinsic Images in the Wild and Shading Annotations in the Wild.

We introduce Intelligent Annotation Dialogs for bounding box annotation. We train an agent to automatically choose a sequence of actions for a human annotator to produce a bounding box in a minimal amount of time. Specifically, we consider two actions: box verification, where the annotator verifies a box generated by an object detector, and manual box drawing. We explore two kinds of agents, one based on predicting the probability that a box will be positively verified, and the other based on reinforcement learning. We demonstrate that (1) our agents are able to learn efficient annotation strategies in several scenarios, automatically adapting to the image difficulty, the desired quality of the boxes, and the detector strength; (2) in all scenarios the resulting annotation dialogs speed up annotation compared to manual box drawing alone and box verification alone, while also outperforming any fixed combination of verification and drawing in most scenarios; (3) in a realistic scenario where the detector is iteratively re-trained, our agents evolve a series of strategies that reflect the shifting trade-off between verification and drawing as the detector grows stronger.

In this paper, we propose a simple yet effective method to learn globally optimized detector for object detection, which is a simple modification to the standard cross-entropy gradient inspired by the REINFORCE algorithm. In our approach, the cross-entropy gradient is adaptively adjusted according to overall mean Average Precision (mAP) of the current state for each detection candidate, which leads to more effective gradient and global optimization of detection results, and brings no computational overhead. Benefiting from more precise gradients produced by the global optimization method, our framework significantly improves state-of-the-art object detectors. Furthermore, since our method is based on scores and bounding boxes without modification on the architecture of object detector, it can be easily applied to off-the-shelf modern object detection frameworks.

This paper proposes a multi-grid method for learning energy-based generative ConvNet models of images. For each grid, we learn an energy-based probabilistic model where the energy function is defined by a bottom-up convolutional neural network (ConvNet or CNN). Learning such a model requires generating synthesized examples from the model. Within each iteration of our learning algorithm, for each observed training image, we generate synthesized images at multiple grids by initializing the finite-step MCMC sampling from a minimal 1 x 1 version of the training image. The synthesized image at each subsequent grid is obtained by a finite-step MCMC initialized from the synthesized image generated at the previous coarser grid. After obtaining the synthesized examples, the parameters of the models at multiple grids are updated separately and simultaneously based on the differences between synthesized and observed examples. We show that this multi-grid method can learn realistic energy-based generative ConvNet models, and it outperforms the original contrastive divergence (CD) and persistent CD.

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe for tasks where acquiring hand labeled data is extremely hard and tedious. In this work, we focus on adapting the representations learned by segmentation networks across synthetic and real domains. Contrary to previous approaches that use a simple adversarial objective or superpixel information to aid the process, we propose an approach based on Generative Adversarial Networks (GANs) that brings the embeddings closer in the learned feature space. To showcase the generality and scalability of our approach, we show that we can achieve state of the art results on two challenging scenarios of synthetic to real domain adaptation. Additional exploratory experiments show that our approach: (1) generalizes to unseen domains and (2) results in improved alignment of source and target distributions.

Learning from web data is increasingly popular due to abundant free web resources. However, the performance gap between webly supervised learning and traditional supervised learning is still very large, due to the label noise of web data. To fill this gap, most existing methods propose to purify or augment web data using instance-level supervision, which generally requires heavy annotation. Instead, we propose to address the label noise by using more accessible category-level supervision. In particular, we build our deep probabilistic framework upon variational autoencoder (VAE), in which classification network and VAE can jointly leverage category-level hybrid information. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed method.

Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as well as large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the art face recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world face recognition problem.

We present a scalable weakly supervised clustering approach to learn facial action units (AUs) from large, freely available web images. Unlike most existing methods (e.g., CNNs) that rely on fully annotated data, our method exploits web images with inaccurate annotations. Specifically, we derive a weakly-supervised spectral algorithm that learns an embedding space to couple image appearance and semantics. The algorithm has efficient gradient update, and scales up to large quantities of images with a stochastic extension. With the learned embedding space, we adopt rank-order clustering to identify groups of visually and semantically similar images, and re-annotate these groups for training AU classifiers. Evaluation on the 1 millon EmotioNet dataset demonstrates the effectiveness of our approach: (1) our learned annotations reach on average 91.3% agreement with human annotations on 7 common AUs, (2) classifiers trained with re-annotated images perform comparably to, sometimes even better than, its supervised CNN-based counterpart, and (3) our method offers intuitive outlier/noise pruning instead of forcing one annotation to every image. Code is available.

The two underlying requirements of face age progression, i.e. aging accuracy and identity permanence, are not well studied in the literature. In this paper, we present a novel generative adversarial network based approach. It separately models the constraints for the intrinsic subject-specific characteristics and the age-specific facial changes with respect to the elapsed time, ensuring that the generated faces present desired aging effects while simultaneously keeping personalized properties stable. Further, to generate more lifelike facial details, high-level age-specific features conveyed by the synthesized face are estimated by a pyramidal adversarial discriminator at multiple scales, which simulates the aging effects in a finer manner. The proposed method is applicable to diverse face samples in the presence of variations in pose, expression, makeup, etc., and remarkably vivid aging effects are achieved. Both visual fidelity and quantitative evaluations show that the approach advances the state-of-the-art.

In this paper, we propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. These problems usually involve the estimation of two components of the target signals: structures and details. Motivated by this, our proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner. The recovered structures and details can generate the target signals according to the formation model for each particular application. The DualCNN is a flexible framework for low-level vision tasks and can be easily incorporated with existing CNNs. Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.

We propose a method to learn a distribution of shape trajectories from longitudinal data, i.e. the collection of individual objects repeatedly observed at multiple time-points. The method allows to compute an average spatiotemporal trajectory of shape changes at the group level, and the individual variations of this trajectory both in terms of geometry and time dynamics. First, we formulate a non-linear mixed-effects statistical model as the combination of a generic statistical model for manifold-valued longitudinal data, a deformation model defining shape trajectories via the action of a finite-dimensional set of diffeomorphisms with a manifold structure, and an efficient numerical scheme to compute parallel transport on this manifold. Second, we introduce a MCMC-SAEM algorithm with a specific approach to shape sampling, an adaptive scheme for proposal variances, and a log-likelihood tempering strategy to estimate our model. Third, we validate our algorithm on 2D simulated data, and then estimate a scenario of alteration of the shape of the hippocampus 3D brain structure during the course of Alzheimer's disease. The method shows for instance that hippocampal atrophy progresses more quickly in female subjects, and occurs earlier in APOE4 mutation carriers. We finally illustrate the potential of our method for classifying pathological trajectories versus normal ageing.

This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the model follows an "analysis by synthesis" scheme and can be interpreted as a mode seeking and mode shifting process. The model can synthesize 3D shape patterns by sampling from the probability distribution via MCMC such as Langevin dynamics. The model can be used to train a 3D generator network via MCMC teaching. The conditional version of the 3D shape descriptor net can be used for 3D object recovery and 3D object super-resolution. Experiments demonstrate that the proposed model can generate realistic 3D shape patterns and can be useful for 3D shape analysis.

The ability to predict depth from a single image - using recent advances in CNNs - is of increasing interest to the vision community. Unsupervised strategies to learning are particularly appealing as they can utilize much larger and varied monocular video datasets during learning without the need for ground truth depth or stereo. In previous works, separate pose and depth CNN predictors had to be determined such that their joint outputs minimized the photometric error. Inspired by recent advances in direct visual odometry (DVO), we argue that the depth CNN predictor can be learned without a pose CNN predictor. Further, we demonstrate empirically that incorporation of a differentiable implementation of DVO, along with a novel depth normalization strategy - substantially improves performance over state of the art that use monocular videos for training.

The world is covered with millions of buildings, and precisely knowing each instance's position and extents is vital to a multitude of applications. Recently, automated building footprint segmentation models have shown superior detection accuracy thanks to the usage of Convolutional Neural Networks (CNN). However, even the latest evolutions struggle to precisely delineating borders, which often leads to geometric distortions and inadvertent fusion of adjacent building instances. We propose to overcome this issue by exploiting the distinct geometric properties of buildings. To this end, we present Deep Structured Active Contours (DSAC), a novel framework that integrates priors and constraints into the segmentation process, such as continuous boundaries, smooth edges, and sharp corners. To do so, DSAC employs Active Contour Models (ACM), a family of constraint- and prior-based polygonal models. We learn ACM parameterizations per instance using a CNN, and show how to incorporate all components in a structured output model, making DSAC trainable end-to-end. We evaluate DSAC on three challenging building instance segmentation datasets, where it compares favorably against state-of-the-art. Code will be made available.

Human free-hand sketches have been studied in various contexts including sketch recognition, synthesis and fine-grained sketch-based image retrieval (FG-SBIR). A fundamental challenge for sketch analysis is to deal with drastically different human drawing styles, particularly in terms of abstraction level. In this work, we propose the first stroke-level sketch abstraction model based on the insight of sketch abstraction as a process of trading off between the recognizability of a sketch and the number of strokes used to draw it. Concretely, we train a model for abstract sketch generation through reinforcement learning of a stroke removal policy that learns to predict which strokes can be safely removed without affecting recognizability. We show that our abstraction model can be used for various sketch analysis tasks including: (1) modeling stroke saliency and understanding the decision of sketch recognition models, (2) synthesizing sketches of variable abstraction for a given category, or reference object instance in a photo, and (3) training a FG-SBIR model with photos only, bypassing the expensive photo-sketch pair collection step.

Face anti-spoofing is crucial to prevent face recognition systems from a security breach. Previous deep learning approaches formulate face anti-spoofing as a binary classification problem. Many of them struggle to grasp adequate spoofing cues and generalize poorly. In this paper, we argue the importance of auxiliary supervision to guide the learning toward discriminative and generalizable cues. A CNN-RNN model is learned to estimate the face depth with pixel-wise supervision, and to estimate rPPG signals with sequence-wise supervision. The estimated depth and rPPG are fused to distinguish live vs. spoof faces. Further, we introduce a new face anti-spoofing database that covers a large range of illumination, subject, and pose variations. Experiments show that our model achieves the state-of-the-art results on both intra- and cross-database testing.

Research on learning suitable feature descriptors for Computer Vision has recently shifted to deep learning where the biggest challenge lies with the formulation of appropriate loss functions, especially since the descriptors to be learned are not known at training time. While approaches such as Siamese and triplet losses have been applied with success, it is still not well understood what makes a good loss function. In this spirit, this work demonstrates that many commonly used losses suffer from a range of problems. Based on this analysis, we introduce mixed-context losses and scale-aware sampling, two methods that when combined enable networks to learn consistently scaled descriptors for the first time.