ECCV 2018 论文列表

Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual tasks and is unable to generalize to other applications. In this paper, we present an efficient end-to-end approach based on deep recurrent network for enforcing temporal consistency in a video.Our method takes the original unprocessed and per-frame processed videos as inputs to produce a temporally consistent video.Consequently, our approach is agnostic to specific image processing algorithms applied on the original video.We train the proposed network by minimizing both short-term and long-term temporal losses as well as the perceptual loss to strike a balance between temporal stability and perceptual similarity with the processed frames.At test time, our model does not require computing optical flow and thus achieves real-time speed even for high-resolution videos. We show that our single model can handle multiple and unseen tasks, including but not limited to artistic style transfer, enhancement, colorization, image-to-image translation and intrinsic image decomposition.Extensive objective evaluation and subject study demonstrate that the proposed approach performs favorably against the state-of-the-art methods on various types of videos.

We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height maps (MLH) where at each grid location, we store multiple instances of height maps, thereby representing 3D shape detail that is hidden behind several layers of occlusion. We provide a novel view merging method for combining view dependent information (Eg. MLH descriptors) from multiple views. Because of the ability of using 2D CNNs our method is highly memory efficient in terms of input resolution compared to the voxel based input. Together with MLH descriptors, and our multi view merging we achieve the state-of-the-art result in classification on ModelNet dataset.

In this paper, we present a novel deep learning framework that derives discriminative local descriptors for 3D surface shapes. In contrast to previous convolutional neural networks (CNNs) that rely on rendering multi-view images or extracting intrinsic shape properties, we parameterize the multi-scale localized neighborhoods of a keypoint into regular 2D grids, which are termed as `geometry images'. The benefits of such geometry images include retaining sufficient geometric information, as well as allowing the usage of standard CNNs. Specifically, we leverage a triplet network to perform deep metric learning, which takes a set of triplets as input, and a newly designed triplet loss function is minimized to distinguish between similar and dissimilar pairs of keypoints. At the testing stage, given a geometry image of a point of interest, our network outputs a discriminative local descriptor for it. Experimental results for non-rigid shape matching on several benchmarks demonstrate the superior performance of our learned descriptors over traditional descriptors and the state-of-the-art learning-based alternatives.

3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data. We propose two anatomically inspired loss functions and use them with a weakly-supervised learning framework to jointly learn from large-scale in-the-wild 2D and indoor/synthetic 3D data. We also present a simple temporal network that exploits temporal and structural cues present in predicted pose sequences to temporally harmonize the pose estimations. We carefully analyze the proposed contributions through loss surface visualizations and sensitivity analysis to facilitate deeper understanding of their working mechanism. Jointly, the two networks capture the anatomical constraints in static and kinetic states of the human body. Our complete pipeline improves the state-of-the-art by 11.8% and 12% on Human3.6M and MPI-INF-3DHP, respectively, and runs at 30 FPS on a commodity graphics card.

We propose and investigate an identity sensitive joint embedding of face and voice. Such an embedding enables cross-modal retrieval from voice to face and from face to voice. We make the following four contributions: first, we show that the embedding can be learnt from videos of talking faces, without requiring any identity labels, using a form of cross-modal self-supervision; second, we develop a curriculum learning schedule for hard negative mining targeted to this task, that is essential for learning to proceed successfully; third, we demonstrate and evaluate cross-modal retrieval for identities unseen and unheard during training over a number of scenarios and establish a benchmark for this novel task; finally, we show an application of using the joint embedding for automatically retrieving and labelling characters in TV dramas.

Camera equipped drones are nowadays being used to explore large scenes and reconstruct detailed 3D maps. When free space in the scene is approximately known, an offline planner can generate optimal plans to efficiently explore the scene. However, for exploring unknown scenes, the planner must predict and maximize usefulness of where to go on the fly. Traditionally, this has been achieved using handcrafted utility functions. We propose to learn a better utility function that predicts the usefulness of future viewpoints. Our learned utility function is based on a 3D convolutional neural network. This network takes as input a novel volumetric scene representation that implicitly captures previously visited viewpoints and generalizes to new scenes. We evaluate our method on several large 3D models of urban scenes using simulated depth cameras. We show that our method outperforms existing utility measures in terms of reconstruction performance and is robust to sensor noise.

We present an approach to infer a layer-structured 3D representation of a scene from a single input image. This allows us to infer not only the depth of the visible pixels, but also to capture the texture and depth for content in the scene that is not directly visible. We overcome the challenge posed by the lack of direct supervision by instead leveraging a more naturally available multi-view supervisory signal. Our insight is to use view synthesis as a proxy task: we enforce that our representation (inferred from a single image), when rendered from a novel perspective, matches the true observed image. We present a learning framework that operationalizes this insight using a new, differentiable novel view renderer. We provide qualitative and quantitative validation of our approach in two different settings, and demonstrate that we can learn to capture the hidden aspects of a scene.

In this paper we present an effcient modeling framework for large scale urban scenes. Taking surface meshes derived from multi- view-stereo systems as input, our algorithm outputs simplied models with semantics at different levels of detail (LODs). Our key observation is that urban building is usually composed of planar roof tops connected with vertical walls. There are two major steps in our framework: segmentation and building modeling. The scene is first segmented into four classes with a Markov random field combining height and image features. In the following modeling step, various 2D line segments sketching the roof boundaries are detected and slice the plane into faces. Through assigning each face with a roof plane, the final model is constructed by extruding the faces to the corresponding planes. By combining geometric and appearance cues together, the proposed method is robust and fast compared to the state-of-the-art algorithms.

We present Lambda Twist; a novel P3P solver which is accurate, fast and robust. Current state-of-the-art P3P solvers find all roots to a quartic and discard geometrically invalid and duplicate solutions in a post-processing step. Instead of solving a quartic, the proposed P3P solver exploits the underlying elliptic equations which can be solved by a fast and numerically accurate diagonalization. This diagonalization requires a single real root of a cubic which is then used to find the, up to four, P3P solutions. Unlike the direct quartic solvers our method never computes geometrically invalid or duplicate solutions. Extensive evaluation on synthetic data shows that the new solver has better numerical accuracy and is faster compared to the state-of-the-art P3P implementations. Implementation and benchmark are available on github.

Multi-codebook quantization (MCQ) is the task of expressing a set of vectors as accurately as possible in terms of discrete entries in multiple bases. Work in MCQ is heavily focused on lowering quantization error, thereby improving distance estimation and recall on benchmarks of visual descriptors at a fixed memory budget. However, recent studies and methods in this area are hard to compare against each other, because they use different datasets, different protocols, and, perhaps most importantly, different computational budgets. In this work, we first benchmark a series of MCQ baselines on an equal footing and provide an analysis of their recall-vs-runtime performance. We observe that local search quantization (LSQ) is in practice much faster than its competitors, but is not the most accurate method in all cases. We then introduce two novel improvements that render LSQ (i) more accurate and (ii) faster. These improvements are easy to implement, and define a new state of the art in MCQ.

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of prediction accuracy between the quantized model and the full-precision model. To address this gap, we propose to jointly train a quantized, bit-operation-compatible DNN and its associated quantizers, as opposed to using fixed, handcrafted quantization schemes such as uniform or logarithmic quantization. Our method for learning the quantizers applies to both network weights and activations with arbitrary-bit precision, and our quantizers are easy to train. The comprehensive experiments on CIFAR-10 and ImageNet datasets show that our method works consistently well for various network structures such as AlexNet, VGG-Net, GoogLeNet, ResNet, and DenseNet, surpassing previous quantization methods in terms of accuracy by an appreciable margin. Code available at https://github.com/Microsoft/LQ-Nets

This paper addresses the single-image compressive sensing (CS) and reconstruction problem. We propose a scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) that enables high-fidelity, flexible and fast CS images reconstruction. LAPRAN progressively reconstructs an image following the concept of the Laplacian pyramid through multiple stages of reconstructive adversarial networks (RANs). At each pyramid level, CS measurements are fused with a contextual latent vector to generate a high-frequency image residual. Consequently, LAPRAN can produce hierarchies of reconstructed images and each with an incremental resolution and improved quality. The scalable pyramid structure of LAPRAN enables high-fidelity CS reconstruction with a flexible resolution that is adaptive to a wide range of compression ratios (CRs), which is infeasible with existing methods. Experimental results on multiple public datasets show that LAPRAN offers an average 7.47dB and 5.98dB PSNR, and an average 57.93% and 33.20% SSIM improvement compared to model-based and data-driven baselines, respectively.

Referring expression image segmentation aims to segment out the object referred by a natural language query expression. Without considering the specific properties of visual and textual information, existing works usually deal with this task by directly feeding a foreground/background classifier with cascaded image and text features, which are extracted from each image region and the whole query, respectively. On the one hand, they ignore that each word in a query expression makes different contributions to identify the desired object, which requires a differential treatment in extracting text feature. On the other hand, the relationships of different image regions are not considered as well, even though they are greatly important to eliminate the undesired foreground object in accordance with specific query. To address aforementioned issues, in this paper, we propose a key-word-aware network, which contains a query attention model and a key-word-aware visual context model. In extracting text features, the query attention model attends to assign higher weights for the words which are more important for identifying object. Meanwhile, the key-word-aware visual context model describes the relationships among different image regions, according to corresponding query. Our proposed method outperforms state-of-the-art methods on two referring expression image segmentation databases.

This work extends popular star-convexity and other more general forms of convexity priors. We represent an object as a union of "convex'' overlappable subsets. Since an arbitrary shape can always be divided into convex parts, our regularization model restricts the number of such parts. Previous k-part shape priors are limited to disjoint parts. For example, one approach segments an object via optimizing its $k$-coverage by disjoint convex parts, which we show is highly sensitive to local minima. In contrast, our shape model allows the convex parts to overlap, which both relaxes and simplifies the coverage problem, e.g. fewer parts are needed to represent any object. As shown in the paper, for many forms of convexity our regularization model is significantly more descriptive for any given k. Our shape prior is useful in practice, e.g. in biomedical applications, and its optimization is robust to local minima.

In this paper, we explore neural network models that learn to associate segments of spoken audio captions with the semantically relevant portions of natural images that they refer to. We demonstrate that these audio-visual associative localizations emerge from network-internal representations learned as a by-product of training to perform an image-audio retrieval task. Our models operate directly on the image pixels and speech waveform, and do not rely on any conventional supervision in the form of labels, segmentations, or alignments between the modalities during training. We perform analysis using the Places 205 and ADE20k datasets demonstrating that our models implicitly learn semantically-coupled object and word detectors.

Compressive video sensing is the process of encoding multiple sub-frames into a single frame with controlled sensor exposures and reconstructing the sub-frames from the single compressed frame. It is known that spatially and temporally random exposures provide the most balanced compression in terms of signal recovery. However, sensors that achieve a fully random exposure on each pixel cannot be easily realized in practice because the circuit of the sensor becomes complicated and incompatible with the sensitivity and resolution.Therefore, it is necessary to design an exposure pattern by considering the constraints enforced by hardware. In this paper, we propose a method of jointly optimizing the exposure patterns of compressive sensing and the reconstruction framework under hardware constraints. By conducting a simulation and actual experiments, we demonstrated that the proposed framework can reconstruct multiple sub-frame images with higher quality.

In this paper, we propose a novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks. TRL can recursively refine the results of both tasks through serialized task-level interactions. In order to mutually-boost for each other, we encapsulate the interaction into a specific Task-Attentional Module (TAM) to adaptively enhance some counterpart patterns of both tasks. Further, to make the inference more credible, we propagate previous learning experiences on both tasks into the next network evolution by explicitly concatenating previous responses. The sequence of task-level interactions are finally evolved along a coarse-to-fine scale space such that the required details may be reconstructed progressively. Extensive experiments on NYU-Depth v2 and SUN RGB-D datasets demonstrate that our method achieves state-of-the-art results for monocular depth estimation and semantic segmentation.

Correlation filter (CF) based trackers generally include two modules, i.e., feature representation and on-line model adaptation. In existing off-line deep learning models for CF trackers, the model adaptation usually is either abandoned or has closed-form solution to make it feasible to learn deep representation in an end-to-end manner. However, such solutions fail to exploit the advances in CF models, and cannot achieve competitive accuracy in comparison with the state-of-the-art CF trackers. In this paper, we investigate the joint learning of deep representation and model adaptation, where an updater network is introduced for better tracking on future frame by taking current frame representation, tracking result, and last CF tracker as input. By modeling the representor as convolutional neural network (CNN), we truncate the alternating direction method of multipliers (ADMM) and interpret it as a deep network of updater, resulting in our model for learning representation and truncated inference (RTINet). Experiments demonstrate that our RTINet tracker achieves favorable tracking accuracy against the state-of-the-art trackers and its rapid version can run at a real-time speed of 24 fps. The code and pre-trained model will be publicly available.

In a world of pervasive cameras, public spaces are often captured from multiple perspectives by cameras of different types, both fixed and mobile. An important problem is to organize these heterogeneous collections of videos by finding connections between them, such as identifying correspondences between the people appearing in the videos and the people holding or wearing the cameras. In this paper, we wish to solve two specific problems: (1) given two or more synchronized third-person videos of a scene, produce a pixel-level segmentation of each visible person and identify corresponding people across different views (i.e., determine who in camera A corresponds with whom in camera B), and (2) given one or more synchronized third-person videos as well as a first-person video taken by a mobile or wearable camera, segment and identify the camera wearer in the third-person videos. Unlike previous work which requires ground truth bounding boxes to estimate the correspondences, we perform person segmentation and identification jointly. We find that solving these two problems simultaneously is mutually beneficial, because better fine-grained segmentation allows us to better perform matching across views, and information from multiple views helps us perform more accurate segmentation. We evaluate our approach on two challenging datasets of interacting people captured from multiple wearable cameras, and show that our proposed method performs significantly better than the state-of-the-art on both person segmentation and identification.