ICCV 2017 Papers

Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, there are many cascade stages. Preceding cascade stages are placed at shallow layers. Easy hard examples are rejected at shallow layers so that the computation for deeper or wider layers is not required. In this way, features and classifiers at latter stages handle more difficult samples with the help of features and classifiers in previous stages. It yields consistent boost in detection performance on PASCAL VOC 2007 and ImageNet for both fast RCNN and Faster RCNN. CC-Net saves computation for both training and testing. Code is available on.

Training deep neural networks is difficult for the pathological curvature problem. Re-parameterization is an effective way to relieve the problem by learning the curvature approximately or constraining the solutions of weights with good properties for optimization. This paper proposes to re-parameterize the input weight of each neuron in deep neural networks by normalizing it with zero-mean and unit-norm, followed by a learnable scalar parameter to adjust the norm of the weight. This technique effectively stabilizes the distribution implicitly. Besides, it improves the conditioning of the optimization problem and thus accelerates the training of deep neural networks. It can be wrapped as a linear module in practice and plugged in any architecture to replace the standard linear module. We highlight the benefits of our method on both multi-layer perceptrons and convolutional neural networks, and demonstrate its scalability and efficiency on SVHN, CIFAR-10, CIFAR-100 and ImageNet datasets.

The complete plenoptic function records radiance of rays from every location, at every angle, for every wavelength and at every time. The signal is multi-dimensional and has long relied on multi-modal sensing such as hybrid light field camera arrays. In this paper, we present a single camera hyperspectral light field imaging solution that we call Snapshot Plenoptic Imager (SPI). SPI uses spectral coded catadioptric mirror arrays for simultaneously acquiring the spatial, angular and spectral dimensions. We further apply a learning-based approach to improve the spectral resolution from very few measurements. Specifically, we demonstrate and then employ a new spectral sparsity prior that allows the hyperspectral profiles to be sparsely represented under a pre-trained dictionary. Comprehensive experiments on synthetic and real data show that our technique is effective, reliable, and accurate. In particular, we are able to produce the first wide FoV multi-spectral light field database.

Fully convolutional network (FCN) has been successfully applied in semantic segmentation of scenes represented with RGB images. Images augmented with depth channel provide more understanding of the geometric information of the scene in the image. The question is how to best exploit this additional information to improve the segmentation performance. In this paper, we present a neural network with multiple branches for segmenting RGB-D images. Our approach is to use the available depth to split the image into layers with common visual characteristic of objects/scenes, or common "scene-resolution". We introduce context-aware receptive field (CaRF) which provides a better control on the relevant contextual information of the learned features. Equipped with CaRF, each branch of the network semantically segments relevant similar scene-resolution, leading to a more focused domain which is easier to learn. Furthermore, our network is cascaded with features from one branch augmenting the features of adjacent branch. We show that such cascading of features enriches the contextual information of each branch and enhances the overall performance. The accuracy that our network achieves outperforms the state-of-the-art methods on two public datasets.

We address the problem of epipolar geometry using the motion of silhouettes. Such methods match epipolar lines or frontier points across views, which are then used as the set of putative correspondences. We introduce an approach that improves by two orders of magnitude the performance over state-of-the-art methods, by significantly reducing the number of outliers in the putative matching. We model the frontier points' correspondence problem as constrained flow optimization, requiring small differences between their coordinates over consecutive frames. Our approach is formulated as a Linear Integer Program and we show that due to the nature of our problem, it can be solved efficiently in an iterative manner. Our method was validated on four standard datasets providing accurate calibrations across very different viewpoints.

We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a specific person or objects in a category. Our approach models an image as a composition of label and latent attributes in a probabilistic model. By varying the fine-grained category label fed into the resulting generative model, we can generate images in a specific category with randomly drawn values on a latent attribute vector. Our approach has two novel aspects. First, we adopt a cross entropy loss for the discriminative and classifier network, but a mean discrepancy objective for the generative network. This kind of asymmetric loss function makes the GAN training more stable. Second, we adopt an encoder network to learn the relationship between the latent space and the real image space, and use pairwise feature matching to keep the structure of generated images. We experiment with natural images of faces, flowers, and birds, and demonstrate that the proposed models are capable of generating realistic and diverse samples with fine-grained category labels. We further show that our models can be applied to other tasks, such as image inpainting, super-resolution, and data augmentation for training better face recognition models.

Discriminative correlation filters (DCFs) have \ryn been shown to perform superiorly in visual tracking. They \ryn only need a small set of training samples from the initial frame to generate an appearance model. However, existing DCFs learn the filters separately from feature extraction, and update these filters using a moving average operation with an empirical weight. These DCF trackers hardly benefit from the end-to-end training. In this paper, we propose the CREST algorithm to reformulate DCFs as a one-layer convolutional neural network. Our method integrates feature extraction, response map generation as well as model update into the neural networks for an end-to-end training. To reduce model degradation during online update, we apply residual learning to take appearance changes into account. Extensive experiments on the benchmark datasets demonstrate that our CREST tracker performs favorably against state-of-the-art trackers.

A novel online algorithm to segment multiple objects in a video sequence is proposed in this work. We develop the collaborative detection, tracking, and segmentation (CDTS) technique to extract multiple segment tracks accurately. First, we jointly use object detector and tracker to generate multiple bounding box tracks for objects. Second, we transform each bounding box into a pixel-wise segment, by employing the alternate shrinking and expansion(ASE) segmentation. Third, we refine the segment tracks, by detecting object disappearance and reappearance cases and merging overlapping segment tracks. Experimental results show that the proposed algorithm significantly surpasses the state-of-the-art conventional algorithms on benchmark datasets.

We present an efficient and automatic approach for accurate reconstruction of instances of big 3D objects from multiple, unorganized and unstructured point clouds, in presence of dynamic clutter and occlusions. In contrast to conventional scanning, where the background is assumed to be rather static, we aim at handling dynamic clutter where background drastically changes during the object scanning. Currently, it is tedious to solve this with available methods unless the object of interest is first segmented out from the rest of the scene. We address the problem by assuming the availability of a prior CAD model, roughly resembling the object to be reconstructed. This assumption almost always holds in applications such as industrial inspection or reverse engineering. With aid of this prior acting as a proxy, we propose a fully enhanced pipeline, capable of automatically detecting and segmenting the object of interest from scenes and creating a pose graph, online, with linear complexity. This allows initial scan alignment to the CAD model space, which is then refined without the CAD constraint to fully recover a high fidelity 3D reconstruction, accurate up to the sensor noise level. We also contribute a novel object detection method, local implicit shape models (LISM) and give a fast verification scheme. We evaluate our method on multiple datasets, demonstrating the ability to accurately reconstruct objects from small sizes up to 125m3.

Pixel-level annotations are expensive and time-consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recent years have seen great progress in weakly-supervised semantic segmentation, whether from a single image or from videos. However, most existing methods are designed to handle a single background class. In practical applications, such as autonomous navigation, it is often crucial to reason about multiple background classes. In this paper, we introduce an approach to doing so by making use of classifier heatmaps. We then develop a two-stream deep architecture that jointly leverages appearance and motion, and design a loss based on our heatmaps to train it. Our experiments demonstrate the benefits of our classifier heatmaps and of our two-stream architecture on challenging urban scene datasets and on the YouTube-Objects benchmark, where we obtain state-of-the-art results.

Existing methods for 3D scene flow estimation often fail in the presence of large displacement or local ambiguities, e.g., at texture-less or reflective surfaces. However, these challenges are omnipresent in dynamic road scenes, which is the focus of this work. Our main contribution is to overcome these 3D motion estimation problems by exploiting recognition. In particular, we investigate the importance of recognition granularity, from coarse 2D bounding box estimates over 2D instance segmentations to fine-grained 3D object part predictions. We compute these cues using CNNs trained on a newly annotated dataset of stereo images and integrate them into a CRF-based model for robust 3D scene flow estimation - an approach we term Instance Scene Flow. We analyze the importance of each recognition cue in an ablation study and observe that the instance segmentation cue is by far strongest, in our setting. We demonstrate the effectiveness of our method on the challenging KITTI 2015 scene flow benchmark where we achieve state-of-the-art performance at the time of submission.

Automatically describing an image with a natural language has been an emerging challenge in both fields of computer vision and natural language processing. In this paper, we present Long Short-Term Memory with Attributes (LSTM-A) - a novel architecture that integrates attributes into the successful Convolutional Neural Networks (CNNs) plus Recurrent Neural Networks (RNNs) image captioning framework, by training them in an end-to-end manner. Particularly, the learning of attributes is strengthened by integrating inter-attribute correlations into Multiple Instance Learning (MIL). To incorporate attributes into captioning, we construct variants of architectures by feeding image representations and attributes into RNNs in different ways to explore the mutual but also fuzzy relationship between them. Extensive experiments are conducted on COCO image captioning dataset and our framework shows clear improvements when compared to state-of-the-art deep models. More remarkably, we obtain METEOR/CIDEr-D of 25.5%/100.2% on testing data of widely used and publicly available splits in [10] when extracting image representations by GoogleNet and achieve superior performance on COCO captioning Leaderboard.

We propose BodyFusion, a novel real-time geometry fusion method that can track and reconstruct non-rigid surface motion of a human performance using a single consumer-grade depth camera. To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method. The key feature of our method is that it jointly solves for both the skeleton and graph-node deformations based on information of the attachments between the skeleton and the graph nodes. The attachments are also updated frame by frame based on the fused surface geometry and the computed deformations. Overall, our method enables increasingly denoised, detailed, and complete surface reconstruction as well as the updating of the skeleton and attachments as the temporal depth frames are fused. Experimental results show that our method exhibits substantially improved nonrigid motion fusion performance and tracking robustness compared with previous state-of-the-art fusion methods. We also contribute a dataset for the quantitative evaluation of fusion-based dynamic scene reconstruction algorithms using a single depth camera.

In this paper, we investigate deep neural networks for blind motion deblurring. Instead of regressing for the motion blur kernel and performing non-blind deblurring out- side of the network (as most methods do), we propose a compact and elegant end-to-end deblurring network. Inspired by the data-driven sparse-coding approaches that are capable of capturing linear dependencies in data, we generalize this notion by embedding non-linearities into the learning process. We propose a new architecture for blind motion deblurring that consists of an autoencoder that learns the data prior, and an adversarial network that attempts to generate and discriminate between clean and blurred features. Once the network is trained, the generator learns a blur-invariant data representation which when fed through the decoder results in the final deblurred output.

Blob detection and image denoising are fundamental, and sometimes related, tasks in computer vision. In this paper, we propose a blob reconstruction method using scale-invariant normalized unilateral second order Gaussian kernels. Unlike other blob detection methods, our method suppresses non-blob structures while also identifying blob parameters, i.e., position, prominence and scale, thereby facilitating blob reconstruction. We present an algorithm for high-ISO long-exposure noise removal that results from the combination of our blob reconstruction method and state-of-the-art denoising methods, i.e., the non-local means algorithm (NLM) and the color version of block-matching and 3-D filtering (CBM3D). Experiments on standard images corrupted by real high-ISO long-exposure noise and real-world noisy images demonstrate that our schemes incorporating the blob reduction procedure outperform both the original NLM and CBM3D.

Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations. Besides the computational gain of having a single network to perform several tasks, we show that object detection and semantic segmentation benefit from each other in terms of accuracy. Experimental results for VOC and COCO datasets show state-of-the-art performance for object detection and segmentation among real time systems.

Deblurring images with outliers has attracted considerable attention recently. However, existing algorithms usually involve complex operations which increase the difficulty of blur kernel estimation. In this paper, we propose a simple yet effective blind image deblurring algorithm to handle blurred images with outliers. The proposed method is motivated by the observation that outliers in the blurred images significantly affect the goodness-of-fit in function approximation. Therefore, we propose an algorithm to model the data fidelity term so that the outliers have little effect on kernel estimation. The proposed algorithm does not require any heuristic outlier detection step, which is critical to the state-of-the-art blind deblurring methods for images with outliers. We analyze the relationship between the proposed algorithm and other blind deblurring methods with outlier handling and show how to estimate intermediate latent images for blur kernel estimation principally. We show that the proposed method can be applied to generic image deblurring as well as non-uniform deblurring. Experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art blind image deblurring methods on both synthetic and real-world images.

Object-to-camera motion produces a variety of apparent motion patterns that significantly affect performance of short-term visual trackers. Despite being crucial for designing robust trackers, their influence is poorly explored in standard benchmarks due to weakly defined, biased and overlapping attribute annotations. In this paper we propose to go beyond pre-recorded benchmarks with post-hoc annotations by presenting an approach that utilizes omnidirectional videos to generate realistic, consistently annotated, short-term tracking scenarios with exactly parameterized motion patterns. We have created an evaluation system, constructed a fully annotated dataset of omnidirectional videos and generators for typical motion patterns. We provide an in-depth analysis of major tracking paradigms which is complementary to the standard benchmarks and confirms the expressiveness of our evaluation approach.

Photorealistic frontal view synthesis from a single face image has a wide range of applications in the field of face recognition. Although data-driven deep learning methods have been proposed to address this problem by seeking solutions from ample face data, this problem is still challenging because it is intrinsically ill-posed. This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details. Four landmark located patch networks are proposed to attend to local textures in addition to the commonly used global encoder-decoder network. Except for the novel architecture, we make this ill-posed problem well constrained by introducing a combination of adversarial loss, symmetry loss and identity preserving loss. The combined loss function leverages both frontal face distribution and pre-trained discriminative deep face models to guide an identity preserving inference of frontal views from profiles. Different from previous deep learning methods that mainly rely on intermediate features for recognition, our method directly leverages the synthesized identity preserving image for downstream tasks like face recognition and attribution estimation. Experimental results demonstrate that our method not only presents compelling perceptual results but also outperforms state-of-the-art results on large pose face recognition.