This paper proposes a new approach for 3D face reconstruction with RGBD images from an inexpensive commodity sensor. The challenges we face are: 1) substantial random noise and corruption are present in low-resolution depth maps; and 2) there is high degree of variability in pose and face expression. We develop a novel two-stage algorithm that effectively maps low-quality depth maps to realistic face models. Each stage is targeted toward a certain type of noise. The first stage extracts sparse errors from depth patches through the data-driven local sparse coding, while the second stage smooths noise on the boundaries between patches and reconstructs the global shape by combining local shapes using our template-based surface refinement. Our approach does not require any markers or user interaction. We perform quantitative and qualitative evaluations on both synthetic and real test sets. Experimental results show that the proposed approach is able to produce high-resolution 3D face models with high accuracy, even if inputs are of low quality, and have large variations in viewpoint and face expression.

Automatic personal clothing retrieval on photo collections, i.e., searching the same clothes worn by the same person, is not a trivial problem as photos are usually taken under completely uncontrolled realistic imaging conditions. Typically, the captured clothing images have large variations due to geometric deformation, occlusion, cluttered background, and photometric variability from illumination and viewpoint, which pose significant challenges to text-based or reranking-based visual search methods. In this paper, a novel framework is presented to tackle these issues by leveraging low-level features (e.g., color) and high-level features (attributes) of clothing. First, a content-based image retrieval (CBIR) approach based on the bag-of-visual-words (BOW) model is developed as our baseline system, in which a codebook is constructed from extracted dominant color patches. A reranking approach is then proposed to improve search quality by exploiting clothing attributes, including the type of clothing, sleeves, patterns, etc. Compared to low-level features, the attributes have better robustness to clothing variations, and carry semantic meanings as high-level image representations. Different visual attribute detectors are learned from large amounts of training data to extract the corresponding attributes. The construction of codebook and building of attribute classifiers are conducted offline, which leads to fast online search performance. Extensive experiments on photo collections show that the reranking algorithm based on attribute learning significantly improves retrieval performance in combination with the proposed baseline. Even our color-based baseline alone outperforms the previous CBIR-based search approaches. The experiments also demonstrate that our approach is robust to large variations of images taken in unconstrained environment.

Active stereo vision is a method of 3D surface scanning involving the projecting and capturing of a series of light patterns where depth is derived from correspondences between the observed and projected patterns. In contrast, passive stereo vision reveals depth through correspondences between textured images from two or more cameras. By employing a projector, active stereo vision systems find correspondences between two or more cameras, without ambiguity, independent of object texture. In this paper, we present a hybrid 3D reconstruction framework that supplements projected pattern correspondence matching with texture information. The proposed scheme consists of using projected pattern data to derive initial correspondences across cameras and then using texture data to eliminate ambiguities. Pattern modulation data are then used to estimate error models from which Kullback-Leibler divergence refinement is applied to reduce misregistration errors. Using only a small number of patterns, the presented approach reduces measurement errors versus traditional structured light and phase matching methodologies while being insensitive to gamma distortion, projector flickering, and secondary reflections. Experimental results demonstrate these advantages in terms of enhanced 3D reconstruction performance in the presence of noise, deterministic distortions, and conditions of texture and depth contrast.

This paper presents a novel system to estimate body pose configuration from a single depth map. It combines both pose detection and pose refinement. The input depth map is matched with a set of pre-captured motion exemplars to generate a body configuration estimation, as well as semantic labeling of the input point cloud. The initial estimation is then refined by directly fitting the body configuration with the observation (e.g., the input depth). In addition to the new system architecture, our other contributions include modifying a point cloud smoothing technique to deal with very noisy input depth maps, a point cloud alignment and pose search algorithm that is view-independent and efficient. Experiments on a public dataset show that our approach achieves significantly higher accuracy than previous state-of-art methods.

Automatic clothes search in consumer photos is not a trivial problem as photos are usually taken under completely uncontrolled realistic imaging conditions. In this paper, a novel framework is presented to tackle this issue by leveraging low-level features (e.g., color) and high-level features (attributes) of clothes. First, a content-based image retrieval(CBIR) approach based on the bag-of-visual-words (BOW) model is developed as our baseline system, in which a codebook is constructed from extracted dominant color patches. A reranking approach is then proposed to improve search quality by exploiting clothes attributes, including the type of clothes, sleeves, patterns, etc. The experiments on photo collections show that our approach is robust to large variations of images taken in unconstrained environment, and the reranking algorithm based on attribute learning significantly improves retrieval performance in combination with the proposed baseline.

The 3D reconstruction of a face from a single frontal image is an ill-posed problem. This is further accentuated when the face image is captured under different poses and/or complex illumination conditions. In this paper, we aim to solve the shape recovery problem from a single facial image under these challenging conditions. The local image models for each patch of facial images and the local surface models for each patch of 3D shape are learned using a non-linear dimensionality reduction technique, and the correspondences between these local models are then learned by a manifold alignment method. By combining the local shapes, the global shape of a face can be reconstructed directly using a single least-square system of equations. We perform experiments on synthetic and real data, and validate the algorithm against the ground truth. Experimental results show that our method can yield accurate shape recovery from out-of-training samples with a variety of pose and illumination variations.

Traditional minimally invasive surgeries use a view port provided by an endoscope or laparoscope. We argue that a useful addition to typical endoscopic imagery would be a global 3-D view providing a wider field of view with explicit depth information for both the exterior and interior of target anatomy. One technical challenge of implementing such a view is finding efficient and accurate means of registering texture images from the laparoscope on prebuilt 3-D surface models of target anatomy derived from magnetic resonance (MR) or computed tomography (CT) images. This paper presents a novel method for addressing this challenge that differs from previous approaches, which depend on tracking the position of the laparoscope. We take advantage of the fact that neighboring frames within a video sequence usually contain enough coherence to allow a 2-D-2-D registration, which is a much more tractable problem. The texturing process can be bootstrapped by an initial 2-D-3-D user-assisted registration of the first video frame followed by mostly-automatic texturing of subsequent frames. We perform experiments on phantom and real data, validate the algorithm against the ground truth, and compare it with the traditional tracking method by simulations. Experiments show that our method improves registration performance compared to the traditional tracking approach.