ICCV 2015 论文列表

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.

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.