Learning to See Through Obstructions With Layered Decomposition.

We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions, or adherent raindrops, from a short sequence of images captured by a moving camera. Our method leverages motion differences between the background and obstructing elements to recover both layers. Specifically, we alternate between estimating dense optical flow fields of the two layers and reconstructing each layer from the flow-warped images via a deep convolutional neural network.

Weakly Supervised Salient Object Detection by Learning A Classifier-Driven Map Generator.

Top-down saliency detection aims to highlight the regions of a specific object category, and typically relies on pixel-wise annotated training data. In this paper, we address the high cost of collecting such training data by a weakly supervised approach to object saliency detection, where only image-level labels, indicating the presence or absence of a target object in an image, are available. The proposed framework is composed of two collaborative CNN modules, an image-level classifier and a pixel-level map generator.

Disambiguating Stereoscopic Transparency Using a Thaumatrope Approach.

Volume rendering is a popular visualization technique for scientific computing and medical imaging. By assigning proper transparency, it allows us to see more information inside the volume. However, because volume rendering projects complex 3D structures into the 2D domain, the resultant visualization often suffers from ambiguity and its spatial relationship could be difficult to recognize correctly, especially when the scene or setting is highly transparent.

Dual-Matrix Sampling for Scalable Translucent Material Rendering.

This paper introduces a scalable algorithm for rendering translucent materials with complex lighting. We represent the light transport with a diffusion approximation by a dual-matrix representation with the Light-to-Surface and Surface-to-Camera matrices. By exploiting the structures within the matrices, the proposed method can locate surface samples with little contribution by using only subsampled matrices and avoid wasting computation on these samples.

Geometrically Consistent Stereoscopic Image Editing Using Patch-Based Synthesis.

This paper presents a patch-based synthesis framework for stereoscopic image editing. The core of the proposed method builds upon a patch-based optimization framework with two key contributions: First, we introduce a depth-dependent patch-pair similarity measure for distinguishing and better utilizing image contents with different depth structures. Second, a joint patch-pair search is proposed for properly handling the correlation between two views.

Augmented multiple instance regression for inferring object contours in bounding boxes.

In this paper, we address the problem of the high annotation cost of acquiring training data for semantic segmentation. Most modern approaches to semantic segmentation are based upon graphical models, such as the conditional random fields, and rely on sufficient training data in form of object contours. To reduce the manual effort on pixel-wise annotating contours, we consider the setting in which the training data set for semantic segmentation is a mixture of a few object contours and an abundant set of bounding boxes of objects.

VisibilityCluster: average directional visibility for many-light rendering.

This paper proposes the VisibilityCluster algorithm for efficient visibility approximation and representation in many-light rendering. By carefully clustering lights and shading points, we can construct a visibility matrix that exhibits good local structures due to visibility coherence of nearby lights and shading points. Average visibility can be efficiently estimated by exploiting the sparse structure of the matrix and shooting only few shadow rays between clusters.

Gradient-free visualization with multiple light approximations.

Gradient computing suffers the noise and ill-definition problems such that local shading is not sufficient for medical imaging to get accurate visualization. However, the current global solutions are either time-consuming or limited to single light source that easily leads misinterpretation. This paper introduces a gradient-free approach to interactively approximate the effects of multiple lights for transparent volume data.

Cross-domain multicue fusion for concept-based video indexing.

The success of query-by-concept, proposed recently to cater to video retrieval needs, depends greatly on the accuracy of concept-based video indexing. Unfortunately, it remains a challenge to recognize the presence of concepts in a video segment or to extract an objective linguistic description from it because of the semantic gap, that is, the lack of correspondence between machine-extracted low-level features and human high-level conceptual interpretation. This paper studies three issues with the aim to reduce such a gap: 1) how to explore cues beyond low-level features, 2) how to combine diverse cues to improve performance, and 3) how to utilize the learned knowledge when applying it to a new domain.