Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera

This paper presents a new method to synthesize an image from arbitrary views and times given a collection of images of a dynamic scene. A key challenge for the novel view synthesis arises from dynamic scene reconstruction where epipolar geometry does not apply to the local motion of dynamic contents. To address this challenge, we propose to combine the depth from single view (DSV) and the depth from multi-view stereo (DMV), where DSV is complete, i.e., a depth is assigned to every pixel, yet view-variant in its scale, while DMV is view-invariant yet incomplete. Our insight is that although its scale and quality are inconsistent with other views, the depth estimation from a single view can be used to reason about the globally coherent geometry of dynamic contents. We cast this problem as learning to correct the scale of DSV, and to refine each depth with locally consistent motions between views to form a coherent depth estimation. We integrate these tasks into a depth fusion network in a self-supervised fashion. Given the fused depth maps, we synthesize a photorealistic virtual view in a specific location and time with our deep blending network that completes the scene and renders the virtual view. We evaluate our method of depth estimation and view synthesis on diverse real-world dynamic scenes and show the outstanding performance over existing methods.

Two-shot Spatially-varying BRDF and Shape Estimation

Capturing the shape and spatially-varying appearance (SVBRDF) of an object from images is a challenging task that has applications in both computer vision and graphics. Traditional optimization-based approaches often need a large number of images taken from multiple views in a controlled environment. Newer deep learning-based approaches require only a few input images, but the reconstruction quality is not on par with optimization techniques. We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. The previous predictions guide each estimation, and a joint refinement network later refines both SVBRDF and shape. We follow a practical mobile image capture setting and use unaligned two-shot flash and no-flash images as input. Both our two-shot image capture and network inference can run on mobile hardware. We also create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Extensive experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images. Comparisons with recent approaches demonstrate the superior performance of the proposed approach.

Convolutional Tensor-Train LSTM for Spatio-temporal Learning

Higher-order Recurrent Neural Networks (RNNs) are effective for long-term forecasting since such architectures can model higher-order correlations and long-term dynamics more effectively. However, higher-order models are expensive and require exponentially more parameters and operations compared with their first-order counterparts. This problem is particularly pronounced in multidimensional data such as videos. To address this issue, we propose Convolutional Tensor-Train Decomposition (CTTD), a novel tensor decomposition with convolutional operations. With CTTD, we construct Convolutional Tensor-Train LSTM (Conv-TT-LSTM) to capture higher-order space-time correlations in videos. We demonstrate that the proposed model outperforms the conventional (first-order) Convolutional LSTM (ConvLSTM) as well as the state-of-the-art ConvLSTM-based approaches in pixel-level video prediction tasks on Moving-MNIST and KTH action datasets, but with much fewer parameters.

Weakly Supervised 3D Hand Pose Estimation via Biomechanical Constraints

Estimating 3D hand pose from 2D images is a difficult, inverse problem due to the inherent scale and depth ambiguities. Current state-of-the-art methods train fully supervised deep neural networks with 3D ground-truth data. However, acquiring 3D annotations is expensive, typically requiring calibrated multi-view setups or labor intensive manual annotations. While annotations of 2D keypoints are much easier to obtain, how to efficiently leverage such weakly-supervised data to improve the task of 3D hand pose prediction remains an important open question. The key difficulty stems from the fact that direct application of additional 2D supervision mostly benefits the 2D proxy objective but does little to alleviate the depth and scale ambiguities. Embracing this challenge we propose a set of novel losses. We show by extensive experiments that our proposed constraints significantly reduce the depth ambiguity and allow the network to more effectively leverage additional 2D annotated images. For example, on the challenging freiHAND dataset using additional 2D annotation without our proposed biomechanical constraints reduces the depth error by only $15\%$, whereas the error is reduced significantly by $50\%$ when the proposed biomechanical constraints are used.

Gaze-Sensing LEDs for Head Mounted Displays

We introduce a new gaze tracker for Head Mounted Displays (HMDs). We modify two off-the-shelf HMDs to be gaze-aware using Light Emitting Diodes (LEDs). Our key contribution is to exploit the sensing capability of LEDs to create low-power gaze tracker for virtual reality (VR) applications. This yields a simple approach using minimal hardware to achieve good accuracy and low latency using light-weight supervised Gaussian Process Regression (GPR) running on a mobile device. With our hardware, we show that Minkowski distance measure based GPR implementation outperforms the commonly used radial basis function-based support vector regression (SVR) without the need to precisely determine free parameters. We show that our gaze estimation method does not require complex dimension reduction techniques, feature extraction, or distortion corrections due to off-axis optical paths. We demonstrate two complete HMD prototypes with a sample eye-tracked application, and report on a series of subjective tests using our prototypes.

Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild

One major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses. In this paper, we address this challenge by proposing a weakly-supervised approach that does not require 3D annotations and learns to estimate 3D poses from unlabeled multi-view data, which can be acquired easily in in-the-wild environments. We propose a novel end-to-end learning framework that enables weakly-supervised training using multi-view consistency. Since multi-view consistency is prone to degenerated solutions, we adopt a 2.5D pose representation and propose a novel objective function that can only be minimized when the predictions of the trained model are consistent and plausible across all camera views. We evaluate our proposed approach on two large scale datasets (Human3.6M and MPII-INF-3DHP) where it achieves state-of-the-art performance among semi-/weakly-supervised methods.

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not necessitate 3D supervision, manually annotated keypoints, multi-view images of an object or a prior 3D template. The key insight of our work is that objects can be represented as a collection of deformable parts, and each part is semantically coherent across different instances of the same category (e.g., wings on birds and wheels on cars). Therefore, by leveraging self-supervisedly learned part segmentation of a large collection of category-specific images, we can effectively enforce semantic consistency between the reconstructed meshes and the original images. This significantly reduces ambiguities during joint prediction of shape and camera pose of an object, along with texture. To the best of our knowledge, we are the first to try and solve the single-view reconstruction problem without a category-specific template mesh or semantic keypoints. Thus our model can easily generalize to various object categories without such labels, e.g., horses, penguins, etc. Through a variety of experiments on several categories of deformable and rigid objects, we demonstrate that our unsupervised method performs comparably if not better than existing category-specific reconstruction methods learned with supervision.

Learning to Generate Multiple Style Transfer Outputs for an Input Sentence

Text style transfer refers to the task of rephrasing a given text in a different style. While various methods have been proposed to advance the state of the art, they often assume the transfer output follows a delta distribution, and thus their models cannot generate different style transfer results for a given input text. To address the limitation, we propose a one-to-many text style transfer framework. In contrast to prior works that learn a one-to-one mapping that converts an input sentence to one output sentence, our approach learns a one-to-many mapping that can convert an input sentence to multiple different output sentences, while preserving the input content. This is achieved by applying adversarial training with a latent decomposition scheme. Specifically, we decompose the latent representation of the input sentence to a style code that captures the language style variation and a content code that encodes the language style-independent content. We then combine the content code with the style code for generating a style transfer output. By combining the same content code with a different style code, we generate a different style transfer output. Extensive experimental results with comparisons to several text style transfer approaches on multiple public datasets using a diverse set of performance metrics validate effectiveness of the proposed approach.

Deep Semantic Face Deblurring

In this paper, we propose an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks. As the human faces are highly structured and share unified facial components (e.g., eyes and mouths), such semantic information provides a strong prior for restoration. We incorporate face semantic labels as input priors and propose an adaptive structural loss to regularize facial local structures within an end-to-end deep convolutional neural network. Specifically, we first use a coarse deblurring network to reduce the motion blur on the input face image. We then adopt a parsing network to extract the semantic features from the coarse deblurred image. Finally, the fine deblurring network utilizes the semantic information to restore a clear face image. We train the network with perceptual and adversarial losses to generate photo-realistic results. The proposed method restores sharp images with more accurate facial features and details. Quantitative and qualitative evaluations demonstrate that the proposed face deblurring algorithm performs favorably against the state-of-the-art methods in terms of restoration quality, face recognition and execution speed.

Discovering Nonlinear Relations with Minimum Predictive Information Regularization

Identifying the underlying directional relations from observational time series with nonlinear interactions and complex relational structures is key to a wide range of applications, yet remains a hard problem. In this work, we introduce a novel minimum predictive information regularization method to infer directional relations from time series, allowing deep learning models to discover nonlinear relations. Our method substantially outperforms other methods for learning nonlinear relations in synthetic datasets, and discovers the directional relations in a video game environment and a heart-rate vs. breath-rate dataset.