CVPR 2015 论文列表

Dense semantic 3D reconstruction is typically formulated as a discrete or continuous problem over label assignments in a voxel grid, combining semantic and depth likelihoods in a Markov Random Field framework. The depth and semantic information is incorporated as a unary potential, smoothed by a pairwise regularizer. However, modelling likelihoods as a unary potential does not model the problem correctly leading to various undesirable visibility artifacts. We propose to formulate an optimization problem that directly optimizes the reprojection error of the 3D model with respect to the image estimates, which corresponds to the optimization over rays, where the cost function depends on the semantic class and depth of the first occupied voxel along the ray. The 2-label formulation is made feasible by transforming it into a graph-representable form under QPBO relaxation, solvable using graph cut. The multi-label problem is solved by applying $\alpha$-expansion using the same relaxation in each expansion move. Our method was indeed shown to be feasible in practice, running comparably fast to the competing methods, while not suffering from ray potential approximation artifacts.

This paper focuses on the problem of hyper-graph matching, by accounting for both unary and higher-order affinity terms. Our method is in line with the linear approximate framework while the problem is iteratively solved in discrete space. It is empirically found more efficient than many extant continuous methods. Moreover, it avoids unknown accuracy loss by heuristic rounding step from the continuous approaches. Under weak assumptions, we prove the iterative discrete gradient assignment in general will trap into a degenerating case -- an m-circle solution path where m is the order of the problem. A tailored adaptive relaxation mechanism is devised to detect the degenerating case and makes the algorithm converge to a fixed point in discrete space. Evaluations on both synthetic and real-world data corroborate the efficiency of our method.

Objects in visual scenes come in a rich variety of transformed states. A few classes of transformation have been heavily studied in computer vision: mostly simple, parametric changes in color and geometry. However, transformations in the physical world occur in many more flavors, and they come with semantic meaning: e.g., bending, folding, aging, etc. The transformations an object can undergo tell us about its physical and functional properties. In this paper, we introduce a dataset of objects, scenes, and materials, each of which is found in a variety of transformed states. Given a novel collection of images, we show how to explain the collection in terms of the states and transformations it depicts. Our system works by generalizing across object classes: states and transformations learned on one set of objects are used to interpret the image collection for an entirely new object class.

In this work we make use of recent advances in data driven classification to improve standard approaches for binocular stereo matching and single view depth estimation. Surface normal direction estimation has become feasible and shown to work reliably on state of the art benchmark datasets. Information about the surface orientation contributes crucial information about the scene geometry in cases where standard approaches struggle. We describe, how the responses of such a classifier can be included in global stereo matching approaches. One of the strengths of our approach is, that we can use the classifier responses for a whole set of directions and let the final optimization decide about the surface orientation. This is important in cases where based on the classifier, multiple different surface orientations seem likely. We evaluate our method on two challenging real-world datasets for the two proposed applications. For the binocular stereo matching we use road scene imagery taken from a car and for the single view depth estimation we use images taken in indoor environments.

Most conventional structure-from-motion (SFM) techniques require camera pose estimation before computing any scene structure. In this work we show that when combined with single/multiple homography estimation, the general Euclidean rigidity constraint provides a simple formulation for scene structure recovery without explicit camera pose computation. This direct structure estimation (DSE) opens a new way to design a SFM system that reverses the order of structure and motion estimation. We show that this alternative approach works well for recovering scene structure and camera poses from sideway motion given planar or general man-made scenes.

In this paper, we focus on complex event detection in internet videos while also providing the key evidences of the detection results. Convolutional Neural Networks (CNNs) have achieved promising performance in image classification and action recognition tasks. However, it remains an open problem how to use CNNs for video event detection and recounting, mainly due to the complexity and diversity of video events. In this work, we propose a flexible deep CNN infrastructure, namely Deep Event Network (DevNet), that simultaneously detects pre-defined events and provides key spatial temporal evidences. Taking key frames of videos as input, we first detect the event of interest at the video level by aggregating the CNN features of the key frames. The pieces of evidences which recount the detection results, are also automatically localized, both temporally and spatially. The challenge is that we only have video level labels, while the key evidences usually take place at the frame levels. Based on the intrinsic property of CNNs, we first generate a spatial-temporal saliency map by back passing through DevNet, which then can be used to find the key frames which are most indicative to the event, as well as to localize the specific spatial position, usually an object, in the frame of the highly indicative area. Experiments on the large scale TRECVID 2014 MEDTest dataset demonstrate the promising performance of our method, both for event detection and evidence recounting.

We develop methods for detector learning which exploit joint training over both weak and strong labels and which transfer learned perceptual representations from strongly-labeled auxiliary tasks. Previous methods for weak-label learning often learn detector models independently using latent variable optimization, but fail to share deep representation knowledge across classes and usually require strong initialization. Other previous methods transfer deep representations from domains with strong labels to those with only weak labels, but do not optimize over individual latent boxes, and thus may miss specific salient structures for a particular category. We propose a model that subsumes these previous approaches, and simultaneously trains a representation and detectors for categories with either weak or strong labels present. We provide a novel formulation of a joint multiple instance learning method that includes examples from classification-style data when available, and also performs domain transfer learning to improve the underlying detector representation. Our model outperforms known methods on ImageNet-200 detection with weak labels.

In the past few years, convolutional neural nets (CNN) have shown incredible promise for learning visual representations. In this paper, we use CNNs for the task of predicting surface normals from a single image. But what is the right architecture? We propose to build upon the decades of hard work in 3D scene understanding to design a new CNN architecture for the task of surface normal estimation. We show that incorporating several constraints (man-made, Manhattan world) and meaningful intermediate representations (room layout, edge labels) in the architecture leads to state of the art performance on surface normal estimation. We also show that our network is quite robust and show state of the art results on other datasets as well without any fine-tuning.

We present a novel view on the indoor visual localization problem, where we avoid the use of interest points and associated descriptors, which are the basic building blocks of most standard methods. Instead, localization is cast as an alignment problem of the edges of the query image to a 3D model consisting of line segments. The proposed strategy is effective in low-textured indoor environments and in very wide baseline setups as it overcomes the dependency of image descriptors on textures, as well as their limited invariance to view point changes. The basic features of our method, which are prevalent indoors, are line segments. As we will show, they allow for defining an efficient Chamfer distance-based aligning cost, computed through integral contour images, incorporated into a first-best-search strategy. Experiments confirm the efectiveness of the method in terms of both, accuracy and computational complexity.

Predicting the depth (or surface normal) of a scene from single monocular color images is a challenging task. This paper tackles this challenging and essentially under-determined problem by regression on deep convolutional neural network (DCNN) features, combined with a post-processing refining step using conditional random fields(CRF). Our framework works at two levels, super-pixel level and pixel level. First, we design a DCNN model to learn the mapping from multi-scale image patches to depth or surface normal values at the super-pixel level. Second, the estimated super-pixel depth or surface normal is refined to the pixel level by exploiting various potentials on the depth or surface normal map, which includes a data term, a smoothness term among super-pixels and an auto-regression term characterizing the local structure of the estimation map. The inference problem can be efficiently solved because it admits a closed-form solution. Experiments on the Make3D and NYU Depth V2 datasets show competitive results compared with recent state-of-the-art methods.

This paper describes a depth image enhancement method for consumer RGB-D cameras. Most existing methods use the pixel-coordinates of the aligned color image. Because the image plane generally has no relationship to the measured surfaces, the global coordinate system is not suitable to handle their local geometries. To improve enhancement accuracy, we use local tangent planes as local coordinates for the measured surfaces. Our method is composed of two steps, a calculation of the local tangents and surface reconstruction. To accurately estimate the local tangents, we propose a color heuristic calculation and an orientation correction using their positional relationships. Additionally, we propose a surface reconstruction method by ray-tracing to local tangents. In our method, accurate depth image enhancement is achieved by using the local geometries approximated by the local tangents. We demonstrate the effectiveness of our method using synthetic and real sensor data. Our method has a high completion rate and achieves the lowest errors in noisy cases when compared with existing techniques.

Light-field cameras are now used in consumer and industrial applications. Recent papers and products have demonstrated practical depth recovery algorithms from a passive single-shot capture. However, current light field capture devices have narrow baselines and constrained spatial resolution; therefore, the accuracy of depth recovery is limited, requiring heavy regularization and producing planar depths that do not resemble the actual geometry. Using shading information is essential to improve the shape estimation. We develop an improved technique for local shape estimation from defocus and correspondence cues, and show how shading can be used to further refine the depth. Light-field cameras are able to capture both spatial and angular data, suitable for refocusing. By locally refocusing each spatial pixel to its respective estimated depth, we produce an all-in-focus image where all viewpoints converge onto a point in the scene. Therefore, the angular pixels have angular coherence, which exhibits three properties: photo consistency, depth consistency, and shading consistency. We propose a new framework that uses angular coherence to optimize depth and shading. The optimization framework estimates both general lighting in natural scenes and shading to improve depth regularization. Our method outperforms current state-of-the-art light-field depth estimation algorithms in multiple scenarios, including real images.

While prior depth from focus and defocus techniques operated on laboratory scenes, we introduce the first depth from focus (DfF) method capable of handling images from mobile phones and other hand-held cameras. Achieving this goal requires solving a novel uncalibrated DfF problem and aligning the frames to account for scene parallax. Our approach is demonstrated on a range of challenging cases and produces high quality results.

We present an approach for tracking camera pose in real time given a stream of depth images. Existing algorithms are prone to drift in the presence of smooth surfaces that destabilize geometric alignment. We show that useful contour cues can be extracted from noisy and incomplete depth input. These cues are used to establish correspondence constraints that carry information about scene geometry and constrain pose estimation. Despite ambiguities in the input, the presented contour constraints reliably improve tracking accuracy. Results on benchmark sequences and on additional challenging examples demonstrate the utility of contour cues for real-time camera pose estimation.

This paper proposes a simple method for estimating dense and accurate optical flow field. It revitalizes an early idea of piecewise parametric flow model. A key innovation is that, we fit a flow field piecewise to a variety of parametric models, where the domain of each piece (i.e., each piece's shape, position and size) is determined adaptively, while at the same time maintaining a global inter-piece flow continuity constraint. We achieve this by a multi-model fitting scheme via energy minimization. Our energy takes into account both the piecewise constant model assumption and the flow field continuity constraint, enabling the proposed method to effectively handle both homogeneous motions and complex motions. The experiments on three public optical flow benchmarks (KITTI, MPI Sintel, and Middlebury) show the superiority of our method compared with the state of the art: it achieves top-tier performances on all the three benchmarks.

We address the challenging problem of recognizing the camera wearer's actions from videos captured by an egocentric camera. Egocentric videos encode a rich set of signals regarding the camera wearer, including head movement, hand pose and gaze information. We propose to utilize these mid-level egocentric cues for egocentric action recognition. We present a novel set of egocentric features and show how they can be combined with motion and object features. The result is a compact representation with superior performance. In addition, we provide the first systematic evaluation of motion, object and egocentric cues in egocentric action recognition. Our benchmark leads to several surprising findings. These findings uncover the best practices for egocentric actions, with a significant performance boost over all previous state-of-the-art methods on three publicly available datasets.

Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct approaches: DPMs are graphical models (Markov random fields), while CNNs are "black-box" non-linear classifiers. In this paper, we show that a DPM can be formulated as a CNN, thus providing a synthesis of the two ideas. Our construction involves unrolling the DPM inference algorithm and mapping each step to an equivalent CNN layer. From this perspective, it is natural to replace the standard image features used in DPMs with a learned feature extractor. We call the resulting model a DeepPyramid DPM and experimentally validate it on PASCAL VOC object detection. We find that DeepPyramid DPMs significantly outperform DPMs based on histograms of oriented gradients features (HOG) and slightly outperforms a comparable version of the recently introduced R-CNN detection system, while running significantly faster.

Continuous-wave time-of-flight (ToF) cameras show great promise as low-cost depth image sensors in mobile applications. However, they also suffer from several challenges, including limited illumination intensity, which mandates the use of large numerical aperture lenses, and thus results in a shallow depth of field, making it difficult to capture scenes with large variations in depth. Another shortcoming is the limited spatial resolution of currently available ToF sensors. In this paper we analyze the image formation model for blurred ToF images. By directly working with raw sensor measurements but regularizing the recovered depth and amplitude images, we are able to simultaneously deblur and super-resolve the output of ToF cameras. Our method outperforms existing methods on both synthetic and real datasets. In the future our algorithm should extend easily to cameras that do not follow the cosine model of continuous-wave sensors, as well as to multi-frequency or multi-phase imaging employed in more recent ToF cameras.

This paper designs a high-performance deep convolutional network (DeepID2+) for face recognition. It is learned with the identification-verification supervisory signal. By increasing the dimension of hidden representations and adding supervision to early convolutional layers, DeepID2+ achieves new state-of-the-art on LFW and YouTube Faces benchmarks. Through empirical studies, we have discovered three properties of its deep neural activations critical for the high performance: sparsity, selectiveness and robustness. (1) It is observed that neural activations are moderately sparse. Moderate sparsity maximizes the discriminative power of the deep net as well as the distance between images. It is surprising that DeepID2+ still can achieve high recognition accuracy even after the neural responses are binarized. (2) Its neurons in higher layers are highly selective to identities and identity-related attributes. We can identify different subsets of neurons which are either constantly excited or inhibited when different identities or attributes are present. Although DeepID2+ is not taught to distinguish attributes during training, it has implicitly learned such high-level concepts. (3) It is much more robust to occlusions, although occlusion patterns are not included in the training set.