Yichen Wei

Saliency Optimization from Robust Background Detection

Recent progresses in salient object detection have exploited the boundary prior, or background information, to assist other saliency cues such as contrast, achieving state-of-the-art results. However, their usage of boundary prior is very simple, fragile, and the integration with other cues is mostly heuristic. In this work, we present new methods to address these issues. First, we propose a robust background measure, called boundary connectivity. It characterizes the spatial layout of image regions with respect to image boundaries and is much more robust. It has an intuitive geometrical interpretation and presents unique benefits that are absent in previous saliency measures. Second, we propose a principled optimization framework to integrate multiple low level cues, including our background measure, to obtain clean and uniform saliency maps. Our formulation is intuitive, efficient and achieves state-of-the-art results on several benchmark datasets.

Face Alignment at 3000 FPS via Regressing Local Binary Features

This paper presents a highly efficient, very accurate regression approach for face alignment. Our approach has two novel components: a set of local binary features, and a locality principle for learning those features. The locality principle guides us to learn a set of highly discriminative local binary features for each facial landmark independently. The obtained local binary features are used to jointly learn a linear regression for the final output. Our approach achieves the state-of-the-art results when tested on the current most challenging benchmarks. Furthermore, because extracting and regressing local binary features is computationally very cheap, our system is much faster than previous methods. It achieves over 3, 000 fps on a desktop or 300 fps on a mobile phone for locating a few dozens of landmarks.

Realtime and Robust Hand Tracking from Depth

We present a realtime hand tracking system using a depth sensor. It tracks a fully articulated hand under large viewpoints in realtime (25 FPS on a desktop without using a GPU) and with high accuracy (error below 10 mm). To our knowledge, it is the first system that achieves such robustness, accuracy, and speed simultaneously, as verified on challenging real data. Our system is made of several novel techniques. We model a hand simply using a number of spheres and define a fast cost function. Those are critical for realtime performance. We propose a hybrid method that combines gradient based and stochastic optimization methods to achieve fast convergence and good accuracy. We present new finger detection and hand initialization methods that greatly enhance the robustness of tracking.

Cascaded hand pose regression

We extends the previous 2D cascaded object pose regression work [9] in two aspects so that it works better for 3D articulated objects. Our first contribution is 3D pose-indexed features that generalize the previous 2D parameterized features and achieve better invariance to 3D transformations. Our second contribution is a principled hierarchical regression that is adapted to the articulated object structure. It is therefore more accurate and faster. Comprehensive experiments verify the state-of-the-art accuracy and efficiency of the proposed approach on the challenging 3D hand pose estimation problem, on a public dataset and our new dataset.

Modeling hair from multiple views

In this paper, we propose a novel image-based approach to model hair geometry from images taken at multiple viewpoints. Unlike previous hair modeling techniques that require intensive user interactions or rely on special capturing setup under controlled illumination conditions, we use a handheld camera to capture hair images under uncontrolled illumination conditions. Our multi-view approach is natural and flexible for capturing. It also provides inherent strong and accurate geometric constraints to recover hair models.In our approach, the hair fibers are synthesized from local image orientations. Each synthesized fiber segment is validated and optimally triangulated from all visible views. The hair volume and the visibility of synthesized fibers can also be reliably estimated from multiple views. Flexibility of acquisition, little user interaction, and high quality results of recovered complex hair models are the key advantages of our method.

Fully Convolutional Instance-Aware Semantic Segmentation

We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation [29] and instance mask proposal [5]. It performs instance mask prediction and classification jointly. The underlying convolutional representation is fully shared between the two sub-tasks, as well as between all regions of interest. The network architecture is highly integrated and efficient. It achieves state-of-the-art performance in both accuracy and efficiency. It wins the COCO 2016 segmentation competition by a large margin. Code would be released at https://github.com/daijifeng001/TA-FCN.

Efficient histogram-based sliding window

Many computer vision problems rely on computing histogram-based objective functions with a sliding window. A main limiting factor is the high computational cost. Existing computational methods have a complexity linear in the histogram dimension. In this paper, we propose an efficient method that has a constant complexity in the histogram dimension and therefore scales well with high dimensional histograms. This is achieved by harnessing the spatial coherence of natural images and computing the objective function in an incremental manner. We demonstrate the significant performance enhancement by our method through important vision tasks including object detection, object tracking and image saliency analysis. Compared with state-of-the-art techniques, our method typically achieves from tens to hundreds of times speedup for those tasks.

Deep Kinematic Pose Regression

Learning articulated object pose is inherently difficult because the pose is high dimensional but has many structural constraints. Most existing work do not model such constraints and does not guarantee the geometric validity of their pose estimation, therefore requiring a post-processing to recover the correct geometry if desired, which is cumbersome and sub-optimal. In this work, we propose to directly embed a kinematic object model into the deep neutral network learning for general articulated object pose estimation. The kinematic function is defined on the appropriately parameterized object motion variables. It is differentiable and can be used in the gradient descent based optimization in network training. The prior knowledge on the object geometric model is fully exploited and the structure is guaranteed to be valid. We show convincing experiment results on a toy example and the 3D human pose estimation problem. For the latter we achieve state-of-the-art result on Human3.6M dataset.

Interactive Offline Tracking for Color Objects

In this paper, we present an interactive offline tracking system for generic color objects. The system achieves 60- 100 fps on a 320 times 240 video. The user can therefore easily refine the tracking result in an interactive way. To fully exploit user input and reduce user interaction, the tracking problem is addressed in a global optimization framework. The optimization is efficiently performed through three steps. First, from users input we train a fast object detector that locates candidate objects in the video based on proposed features called boosted color bin. Second, we exploit the temporal coherence to generate multiple object trajectories based on a global best-first strategy. Last, an optimal object path is found by dynamic programming.

Object proposal by multi-branch hierarchical segmentation

Hierarchical segmentation based object proposal methods have become an important step in modern object detection paradigm. However, standard single-way hierarchical methods are fundamentally flawed in that the errors in early steps cannot be corrected and accumulate. In this work, we propose a novel multi-branch hierarchical segmentation approach that alleviates such problems by learning multiple merging strategies in each step in a complementary manner, such that errors in one merging strategy could be corrected by the others. Our approach achieves the state-of-the-art performance for both object proposal and object detection tasks, comparing to previous object proposal methods.