Image Representations for Style Retrieval, Recognition and Background Replacement Tasks

Siddhartha Gairola

Abstract

Replacing overexposed or dull skies in outdoor photographs is a desirable photo manipulation. It is often necessary to color correct the foreground after replacement to make it consistent with the new sky. Methods have been proposed to automate the process of sky replacement and color correction. However, many times a color correction is unwanted by the artist or may produce unrealistic results. Style similarity is an important measure for many applications such as style transfer, fashion search, art exploration, etc. However, computational modeling of style is a difficult task owing to its vague and subjective nature. Most methods for style based retrieval use supervised training with pre-defined categorization of images according to style. While this paradigm is suitable for applications where style categories are well-defined and curating large datasets according to such a categorization is feasible, in several other cases such a categorization is either ill-defined or does not exist. In this thesis, we primarily study various image representations and their applications in understanding visual style and automatic background replacement. First, we propose a data-driven approach to sky-replacement that avoids color correction by finding a diverse set of skies that are consistent in color and natural illumination with the query image foreground. Our database consists of ∼1200 natural images spanning many outdoor categories. Given a query image, we retrieve the most consistent images from the database according to L2 similarity in feature space and produce candidate composites. The candidates are re-ranked based on realism and diversity. We used pre-trained CNN features and a rich set of hand-crafted features that encode color statistics, structural layout, and natural illumination statistics, but observed color statistics to be the most effective for this task. We share our findings on feature selection and show qualitative results and a user-study based evaluation to show the effectiveness of the proposed method. Next, we propose an unsupervised protocol for learning a neural embedding of visual style of images. Our protocol for learning style based representations does not leverage categorical labels but a proxy measure for forming triplets of anchor, similar, and dissimilar images. Using these triplets, we learn a compact style embedding that is useful for style-based search and retrieval. The learned embeddings outperform other unsupervised representations for style-based image retrieval task on six datasets that capture different meanings of style. We also show that by fine-tuning the learned features with datasetspecific style labels, we obtain best results for image style recognition task on five of the six datasets. To the best of our knowledge, ours is the first work that provides a comprehensive review and evaluation of style representations in an unsupervised setting. Our findings along with the curated outdoor scene database would be useful to the community for future research in the direction of sky-search and sky-replacement

Year of completion:  April 2020
 Advisor : P J Narayanan

Related Publications

    Downloads

    thesis

    Towards developing a multiple modality fusion technique for automatic detection of Glaucoma

    Divya Jyothi Gaddipati

    Abstract

    Glaucoma is a major eye disease which when untreated, can gradually lead to irreversible loss in vision. The underlying causes are a loss of retinal nerve fibres (resulting in a thinning of the layer and enlargement of the optic cup) and peripapillary atrophy. Since these occur without any sign of symptoms in the initial stages, it is difficult to diagnose the disease in the early stages. Hence, the development of Computer-aided diagnostics (CAD) systems for early detection and treatment of the disease has attracted the attention of many medical experts and researchers alike. Optical Coherence Tomography (OCT) and Fundus photography are two widely used retinal imaging techniques for obtaining the structural information of the eye which helps to analyze and detect the diseases. Existing automated systems rely largely on fundus images for assessment of glaucoma due to their fast acquisition and cost. OCT images provide vital and unambiguous information for understanding the changes occurring in the retina, specifically related to the retinal nerve fiber layer and the optic nerve head which are essential for disease assessment. However, the high cost of OCT is a deterrent for deployment in screening at large scale. Hence, the focus of this thesis is to investigate the potential of integrating the two retinal imaging techniques which provide complementary information of the eye for developing automatic glaucoma screening system. Firstly, we propose a deep learning approach directly operating on 3D OCT volumes for glaucoma assessment which showed promising results, thus demonstrating the prominence of the highly discriminative features learnt from OCT for automated glaucoma detection. Next, we present a novel CAD solution wherein both OCT and fundus modality images are leveraged to learn a model that can perform a mapping of fundus to the OCT feature space. We show how this model can be subsequently used to detect glaucoma given an image from only one modality (fundus), thus enabling the automated screening operation to be executed on a large scale. The results show that fundus to OCT feature space mapping is an attractive option for glaucoma detection

    Year of completion:  February 2020
     Advisor : Jayanthi Sivaswamy

    Related Publications

      Downloads

      thesis

      Deep-Learning Features, Graphs and Scene Understanding

      Abhijeet Kumar

      Abstract

      Scene Understanding has been a major aspiration of computer vision from its early days. Its root lies in enabling the computer/robot/machine to understand, interpret and manipulate visual data, in similarity to what an average human eye does in front of a natural/artificial localized location/scene. This ennoblement of the machine have a widespread impact ranging from Surveillance, Aerial Imaging, Autonomous Navigation, Smart Cities and thus scene understanding have remained as an active area of research in the last decade. In the last decade, the scope of problems in the scene understanding community has broadened from Image Annotation, Image Captioning, Image Segmentation to Object Detection, Dense Image Captioning, Instance Segmentation etc. Advanced problems like Autonomous Navigation, Panoptic Segmentation, Video Summarization, Multi-Person Tracking in Crowded Scenes have also surfaced in this arena and are being vigorously attempted. Deep Learning has played a major role in this advancement/development. The performance metrics in some of these tasks have more than tripled in the last decade itself but these tasks remain far from solved. Success originating from deep learning can be attributed to the learned features. In simple words, features learned from a Convolutional Neural Network trained for annotation are in general far more suited for captioning then a non-deep learning method trained for captioning. Taking cue from this particular deep learning trend, we dived into the domain of scene understanding with the focus on utilization of prelearned-features from other similar domains. We focus on two tasks in particular: Automatic (multi-label)Image Annotation and (Road)Intersection Recognition. Automatic image annotation is one of the earliest problems in scene understanding and refers to the task of assigning (multiple) labels to an image based on its content. Whereas intersection recognition is the outcome of the new era of problems in scene understanding and it refers to the task of identifying an intersection from varied viewpoints in varied weather and lighting conditions. We focused on this significantly varied task approach to broaden the scope and generalizing capability of the results we compute. Both image annotation and intersection recognition pose some common challenges such as occlusion, perspective variations, distortions etc. While focusing on the image annotation task we further narrowed our domain by focusing on graph based methods. We again chose two different paradigms: a multiple kernel learning based non-deep learning approach and a deep-learning based approach, with a focus on bringing out contrast again. Through quantitative and qualitative results we show slightly boosted performance from the above mentioned paradigms. The intersection recognition task is relatively new in the field. Most of the work in field focuses on Places Recognition which utilized only single images. We focus on temporal information i.e. the traversal of the intersection/places as seen from a camera mounted on a vehicle. Through experiments we show a performance boost in intersection recognition from the inclusion of temporal information

      Year of completion:  January 2020
       Advisor : Avinash Sharma

      Related Publications

        Downloads

        thesis

        Computational Imaging Techniques to Recover Omni3D Structure & Surface Properties

        Rajat Aggarwal

        Abstract

        The process of imaging converts a 3D world into a 2D image. This process is inherently lossy, making the problem of understanding the world, ill-posed. During the imaging process, a light ray emanating from a source bounces of different surfaces, interacting with them according to the surface properties (albedo, color, specularity) before reaching the camera. The structure that we see in an image is primarily based on the final surface from which the light was reflected, except when that surface is highly specular (mirror-like). In this work, we explore imaging techniques the recover both the structure and surface properties of a scene. For structure recovery, we extend the idea of stereo imaging and present a practical solution to capture a complete 360◦ panorama using a single camera. Current approaches either use a moving camera for capturing multiple images of a scene, which are then stitched together to form the final panorama, or use multiple cameras that are synchronized. A moving camera limits the solution to static scenes, while multi-camera solutions require dedicated calibrated setups. Our approach improves upon the existing solutions in two significant ways: It solves the problem using a single camera, thus minimizing the calibration problem and providing us the ability to convert any digital camera into a stereo panoramic capture device. It captures all the light rays required for stereo panoramas in a single frame using a compact custom designed mirror, thus making the design practical to manufacture and easier to use. We analyze the optimality of the design as well as present panoramic stereo and depth estimation results. The methods for structure recovery, including stereo are often fooled when the surface is highly specular. To alleviate this, we propose an active-illumination based method to detect and segment mirror-like surfaces in a scene. In computer vision, many active illumination techniques employ Projector-Camera systems to extract useful information from the scenes. Known illumination patterns are projected onto the scene and their deformations in the captured images are then analyzed. We observe that the local frequencies in the captured pattern for the mirror-like surfaces is different from the projected pattern. This property allows us to design a custom Projector-Camera system to segment mirror-like surfaces by analyzing the local frequencies in the captured images. The system projects a sinusoidal pattern and capture the images from projector’s point of view. We present segmentation results for the scenes including multiple reflections and inter-reflections from the mirror-like surfaces. The method can further be used in the separation of direct and global components for the mirror-like surfaces by illuminating the non-mirror-like objects separately. We show how our method is also useful for accurate estimation of shape of the non-mirror-like regions in the presence of mirror-like regions in a scene.

        Year of completion:  November 2019
         Advisor : Anoop M Namboodiri

        Related Publications

          Downloads

          thesis

          Driver Attention Monitoring using Facial Features

          Isha Dua

          Abstract

          How can we assess the quality of human driving using AI? Driver inattention is one of the leading causes of vehicle crashes and incidents worldwide. Driver inattention includes driver fatigue leading to drowsiness and driver distraction, say due to the use of cellphone or rubbernecking, all of which leads to a lack of situational awareness. Hitherto, techniques presented to monitor driver attention evaluated factors such as fatigue and distraction independently. However, to develop a robust driver attention monitoring system, all the factors affecting a driver’s attention needs to be analyzed holistically. In this thesis, we present two novel approaches for driver attention analysis on the road using driver video and fusion of driver and road video.
          In the first approach, we propose the driver attention rating system that leverages the front camera of a windshield-mounted smartphone to monitor the driver attention by combining several features. We derive a driver attention rating by fusing spatio-temporal features based on the driver state and behavior such as head pose, eye gaze, eye closure, yawns, use of cellphones, etc. We present a few architec- tures for feature aggregation like AutoRate and Attention-based AutoRate. We perform an extensive evaluation of feature aggregation networks on real-world driving data and also data from controlled, static vehicle settings with 30 drivers in a large city. We compare the proposed method’s automatically- generated rating with the scores given by 5 human annotators. We introduce the kappa coefficient, an evaluation metric to compute the inter-rater agreement between the generated rating and the rating pro- vided by human annotators. We observe that Attention-based AutoRate outperforms other proposed designs for feature aggregation by 10%. Further, we use the learned temporal and spatial attention to visualize the key frame and the key action, which justifies the model’s predicted rating. Finally, to pro- vide driver-specific results, we fine-tune the Attention-based AutoRate model using the specific driver data to give personalized driver experience.

          Year of completion:  June 2020
           Advisor : Prof. C.V. Jawahar

          Related Publications

            Downloads

            thesis

            More Articles …

            1. An investigation of the annotated data sparsity problem in the medical domain
            2. Document Image Quality Assessment
            3. Computational Video Editing and Re-editing
            4. Geometric + Kinematic Priors and Part-based Graph Convolutional Network for Skeleton-based Human Action Recognition