ICCV 2015 Papers

We present a multiscale approach for minimizing the energy associated with Markov Random Fields (MRFs) with energy functions that include arbitrary pairwise potentials. The MRF is represented on a hierarchy of successively coarser scales, where the problem on each scale is itself an MRF with suitably defined potentials. These representations are used to construct an efficient multiscale algorithm that seeks a minimal-energy solution to the original problem. The algorithm is iterative and features a bidirectional crosstalk between fine and coarse representations. We use consistency criteria to guarantee that the energy is nonincreasing throughout the iterative process. The algorithm is evaluated on real-world datasets, achieving competitive performance in relatively short run-times.

Graph matching has a wide spectrum of real-world applications and in general is known NP-hard. In many vision tasks, one realistic problem arises for finding the global node mappings across a batch of corrupted weighted graphs. This paper is an attempt to connect graph matching, especially multi-graph matching to the matrix decomposition model and its relevant on-the-shelf convex optimization algorithms. Our method aims to extract the common inliers and their synchronized permutations from disordered weighted graphs in the presence of deformation and outliers. Under the proposed framework, several variants can be derived in the hope of accommodating to other types of noises. Experimental results on both synthetic data and real images empirically show that the proposed paradigm exhibits several interesting behaviors and in many cases performs competitively with the state-of-the-arts.

This paper presents a new generalized (or ray-pixel, raxel) camera calibration algorithm for camera systems involving distortions by unknown refraction and reflection processes. The key idea is use of intersections of calibration planes, while conventional methods utilized collinearity constraints of points on the planes. We show that intersections of calibration planes can realize a simple linear algorithm, and that our method can be applied to any ray-distributions while conventional methods require knowing the ray-distribution class in advance. Evaluations using synthesized and real datasets demonstrate the performance of our method quantitatively and qualitatively.

Multilinear face models are widely used to model the space of human faces with expressions. For databases of 3D human faces of different identities performing multiple expressions, these statistical shape models decouple identity and expression variations. To compute a high-quality multilinear face model, the quality of the registration of the database of 3D face scans used for training is essential. Meanwhile, a multilinear face model can be used as an effective prior to register 3D face scans, which are typically noisy and incomplete. Inspired by the minimum description length approach, we propose the first method to jointly optimize a multilinear model and the registration of the 3D scans used for training. Given an initial registration, our approach fully automatically improves the registration by optimizing an objective function that measures the compactness of the multilinear model, resulting in a sparse model. We choose a continuous representation for each face shape that allows to use a quasi-Newton method in parameter space for optimization. We show that our approach is computationally significantly more efficient and leads to correspondences of higher quality than existing methods based on linear statistical models. This allows us to evaluate our approach on large standard 3D face databases and in the presence of noisy initializations.

The problem of estimating a full BRDF from partial observations has already been studied using either parametric or non-parametric approaches. The goal in each case is to best match this sparse set of input measurements. In this paper we address the problem of inferring higher order reflectance information starting from the minimal input of a single BRDF slice. We begin from the prototypical case of a homogeneous sphere, lit by a head-on light source, which only holds information about less than 0.001% of the whole BRDF domain. We propose a novel method to infer the higher dimensional properties of the material's BRDF, based on the statistical distribution of known material characteristics observed in real-life samples. We evaluated our method based on a large set of experiments generated from real-world BRDFs and newly measured materials. Although inferring higher dimensional BRDFs from such modest training is not a trivial problem, our method performs better than state-of-the-art parametric, semi-parametric and non-parametric approaches. Finally, we discuss interesting applications on material re-lighting, and flash-based photography.

This paper presents a data-driven matching cost for stereo matching. A novel deep visual correspondence embedding model is trained via Convolutional Neural Network on a large set of stereo images with ground truth disparities. This deep embedding model leverages appearance data to learn visual similarity relationships between corresponding image patches, and explicitly maps intensity values into an embedding feature space to measure pixel dissimilarities. Experimental results on KITTI and Middlebury data sets demonstrate the effectiveness of our model. First, we prove that the new measure of pixel dissimilarity outperforms traditional matching costs. Furthermore, when integrated with a global stereo framework, our method ranks top 3 among all two-frame algorithms on the KITTI benchmark. Finally, cross-validation results show that our model is able to make correct predictions for unseen data which are outside of its labeled training set.

In the past decades, hundreds of saliency models have been proposed for fixation prediction, along with dozens of evaluation metrics. However, existing metrics, which are often heuristically designed, may draw conflict conclusions in comparing saliency models. As a consequence, it becomes somehow confusing on the selection of metrics in comparing new models with state-of-the-arts. To address this problem, we propose a data-driven metric for comprehensive evaluation of saliency models. Instead of heuristically designing such a metric, we first conduct extensive subjective tests to find how saliency maps are assessed by the human-being. Based on the user data collected in the tests, nine representative evaluation metrics are directly compared by quantizing their performances in assessing saliency maps. Moreover, we propose to learn a data-driven metric by using Convolutional Neural Network. Compared with existing metrics, experimental results show that the data-driven metric performs the most consistently with the human-being in evaluating saliency maps as well as saliency models.

In this paper, we provide a new, real photo dataset with precise ground-truth for intrinsic image research. Prior ground-truth datasets have been restricted to rather simple illumination conditions and scene geometries, or have been enhanced using image synthesis methods. The dataset provided in this paper is based on complex multi-illuminant scenarios under multi-colored illumination conditions and challenging cast shadows. We provide full per-pixel intrinsic ground-truth data for these scenarios, i.e. reflectance, specularity, shading, and illumination for scenes as well as preliminary depth information. Furthermore, we evaluate 3 state-of-the-art intrinsic image recovery methods, using our dataset.

Collaborative filtering aims to predict unknown user ratings in a recommender system by collectively assessing known user preferences. In this paper, we first draw analogies between collaborative filtering and the pose estimation problem. Specifically, we recast the hand pose estimation problem as the cold-start problem for a new user with unknown item ratings in a recommender system. Inspired by fast and accurate matrix factorization techniques for collaborative filtering, we develop a real-time algorithm for estimating the hand pose from RGB-D data of a commercial depth camera. First, we efficiently identify nearest neighbors using local shape descriptors in the RGB-D domain from a library of hand poses with known pose parameter values. We then use this information to evaluate the unknown pose parameters using a joint matrix factorization and completion (JMFC) approach. Our quantitative and qualitative results suggest that our approach is robust to variation in hand configurations while achieving real time performance (29 FPS) on a standard computer.

Comparing two images from different views has been a long-standing challenging problem in computer vision, as visual features are not stable under large view point changes. In this paper, given a single input image of an object, we synthesize its features for other views, leveraging an existing modestly-sized 3D model collection of related but not identical objects.To accomplish this, we study the relationship of image patches between different views of the same object, seeking what we call surrogate patches -- patches in one view whose feature content predicts well the features of a patch in another view. Based upon these surrogate relationships, we can create feature sets for all views of the latent object on a per patch basis, providing us an augmented multi-view representation of the object. We provide theoretical and empirical analysis of the feature synthesis process, and evaluate the augmented features in fine-grained image retrieval/recognition and instance retrieval tasks. Experimental results show that our synthesized features do enable view-independent comparison between images and perform significantly better than other traditional approaches in this respect.

Given an Internet photo collection of a landmark, we compute a 3D time-lapse video sequence where a virtual camera moves continuously in time and space. While previous work assumed a static camera, the addition of camera motion during the time-lapse creates a very compelling impression of parallax. Achieving this goal, however, requires addressing multiple technical challenges, including solving for time-varying depth maps, regularizing 3D point color profiles over time, and reconstructing high quality, hole-free images at every frame from the projected profiles. Our results show photorealistic time-lapses of skylines and natural scenes over many years, with dramatic parallax effects.

A novel structured light method for color 3D surface profilometry is proposed. The proposed method does not require color calibration of a camera-projector pair and may be used for reconstruction of both dynamic and static scenes. The method uses a structured light pattern that is a combination of a De Bruijn color sequence and of a sinusoidal fringe. For dynamic scenes a Hessian ridge detector and a Gaussian mixture model are combined to extract stripe centers and to identify color. Stripes are then uniquely identified using dynamic programming based on the Smith-Waterman algorithm and a De Bruijn window property. For static scenes phase-shifting and De Bruijn window property are combined to obtain a high accuracy reconstruction. We have tested the proposed method on multiple objects with challenging surfaces and different albedos that demonstrate usability and robustness of the method.

Recent advances have enabled 3d object reconstruction approaches using a single off-the-shelf RGB-D camera. Although these approaches are successful for a wide range of object classes, they rely on stable and distinctive geometric or texture features. Many objects like mechanical parts, toys, household or decorative articles, however, are textureless and characterized by minimalistic shapes that are simple and symmetric. Existing in-hand scanning systems and 3d reconstruction techniques fail for such symmetric objects in the absence of highly distinctive features. In this work, we show that extracting 3d hand motion for in-hand scanning effectively facilitates the reconstruction of even featureless and highly symmetric objects and we present an approach that fuses the rich additional information of hands into a 3d reconstruction pipeline, significantly contributing to the state-of-the-art of in-hand scanning.

In this paper, we propose a real-time 3D hand pose estimation algorithm using the randomized decision forest framework. Our algorithm takes a depth image as input and generates a set of skeletal joints as output. Previous decision forest-based methods often give labels to all points in a point cloud at a very early stage and vote for the joint locations. By contrast, our algorithm only tracks a set of more flexible virtual landmark points, named segmentation index points (SIPs), before reaching the final decision at a leaf node. Roughly speaking, a SIP represents the centroid of a subset of skeletal joints, which are to be located at the leaves of the branch expanded from the SIP. Inspired by recent latent regression forest-based hand pose estimation framework (Tang et al. 2014), we integrate SIP into the framework with several important improvements: First, we devise a new forest growing strategy, whose decision is made using a randomized feature guided by SIPs. Second, we speed-up the training procedure since only SIPs, not the skeletal joints, are estimated at non-leaf nodes. Third, the experimental results on public benchmark datasets show clearly the advantage of the proposed algorithm over previous state-of-the-art methods, and our algorithm runs at 55.5 fps on a normal CPU without parallelism.

This paper studies matching of fragmented objects to recompose their original geometry. Solving this geometric reassembly problem has direct applications in archaeology and forensic investigation in the computer-aided restoration of damaged artifacts and evidence. We develop a new algorithm to effectively integrate both guidance from a template and from matching of adjacent pieces' fracture-regions. First, we compute partial matchings between fragments and a template, and pairwise matchings among fragments. Many potential matches are obtained and then selected/refined in a multi-piece matching stage to maximize global groupwise matching consistency. This pipeline is effective in composing fragmented thin-shell objects containing small pieces, whose pairwise matching is usually unreliable and ambiguous and hence their reassembly remains challenging to the existing algorithms.