Scene flow estimation has been receiving increasing attention for 3D environment perception. Monocular scene flow estimation -- obtaining 3D structure and 3D motion from two temporally consecutive images -- is a highly ill-posed problem, and practical solutions are lacking to date. We propose a novel monocular scene flow method that yields competitive accuracy and real-time performance. By taking an inverse problem view, we design a single convolutional neural network (CNN) that successfully estimates depth and 3D motion simultaneously from a classical optical flow cost volume. We adopt self-supervised learning with 3D loss functions and occlusion reasoning to leverage unlabeled data. We validate our design choices, including the proxy loss and augmentation setup. Our model achieves state-of-the-art accuracy among unsupervised/self-supervised learning approaches to monocular scene flow, and yields competitive results for the optical flow and monocular depth estimation sub-tasks. Semi-supervised fine-tuning further improves the accuracy and yields promising results in real-time.

Self-Supervised Monocular Scene Flow Estimation

Dense 3D facial motion capture from only monocular in-the-wild pairs of RGB images is a highly challenging problem with numerous applications, ranging from facial expression recognition to facial reenactment. In this work, we propose DeepFaceFlow, a robust, fast, and highly-accurate framework for the dense estimation of 3D non-rigid facial flow between pairs of monocular images. Our DeepFaceFlow framework was trained and tested on two very large-scale facial video datasets, one of them of our own collection and annotation, with the aid of occlusion-aware and 3D-based loss function. We conduct comprehensive experiments probing different aspects of our approach and demonstrating its improved performance against state-of-the-art flow and 3D reconstruction methods. Furthermore, we incorporate our framework in a full-head state-of-the-art facial video synthesis method and demonstrate the ability of our method in better representing and capturing the facial dynamics, resulting in a highly-realistic facial video synthesis. Given registered pairs of images, our framework generates 3D flow maps at 60 fps.

/pdf/deepfaceflow-in-the-wild-dense-3d-facial-motion-estimation-28rhxalahh.pdf

DeepFaceFlow: In-the-Wild Dense 3D Facial Motion Estimation

There is a growing consensus in computer vision that symmetric optical flow estimation constitutes a better model than a generic asymmetric one for its independence of the selection of source/target image. Yet, convolutional neural networks (CNNs), that are considered the de facto standard vision model, deal with the asymmetric case only in most cutting-edge CNNs-based optical flow techniques. We bridge this gap by introducing a novel model named SDOF-GAN: symmetric dense optical flow with generative adversarial networks (GANs). SDOF-GAN realizes a consistency between the forward mapping (source-to-target) and the backward one (target-to-source) by ensuring that they are inverse of each other with an inverse network. In addition, SDOF-GAN leverages a GAN model for which the generator estimates symmetric optical flow fields while the discriminator differentiates the “real” ground-truth flow field from a “fake” estimation by assessing the flow warping error. Finally, SDOF-GAN is trained in a semi-supervised fashion to enable both the precious labeled data and large amounts of unlabeled data to be fully-exploited. We demonstrate significant performance benefits of SDOF-GAN on five publicly-available datasets in contrast to several representative state-of-the-art models for optical flow estimation.

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks

The problem of Scene flow estimation in depth videos has been attracting attention of researchers of machine vision, due to its potential application in various areas of robotics. The conventional scene flow estimation methods are difficult to use in real-time applications due to their long computational overhead. We propose a conditional adversarial network SceneFlowGAN for scene flow estimation. The proposed SceneFlowGAN uses loss function at two ends: both the generator and the discriminator. The proposed network is a first attempt to estimate scene flow using generative adversarial networks, and is able to estimate both the optical flow and disparity from the input stereo images simultaneously. The proposed method is experimented on a huge RGB-D benchmark sceneflow estimation dataset.

A Conditional Adversarial Network for Scene Flow Estimation

Dense 3D facial motion capture from only monocular in-the-wild pairs of RGB images is a highly challenging problem with numerous applications, ranging from facial expression recognition to facial reenactment. In this work, we propose DeepFaceFlow, a robust, fast, and highly-accurate framework for the dense estimation of 3D non-rigid facial flow between pairs of monocular images. Our DeepFaceFlow framework was trained and tested on two very large-scale facial video datasets, one of them of our own collection and annotation, with the aid of occlusion-aware and 3D-based loss function. We conduct comprehensive experiments probing different aspects of our approach and demonstrating its improved performance against state-of-the-art flow and 3D reconstruction methods. Furthermore, we incorporate our framework in a full-head state-of-the-art facial video synthesis method and demonstrate the ability of our method in better representing and capturing the facial dynamics, resulting in a highly-realistic facial video synthesis. Given registered pairs of images, our framework generates 3D flow maps at ~60 fps.

DeepFaceFlow: In-the-wild Dense 3D Facial Motion Estimation

Estimating scene flow in RGB-D videos is attracting much interest of the computer vision researchers, due to its potential applications in robotics. The state-of-the-art techniques for scene flow estimation typically rely on the knowledge of scene structure of the frame and the correspondence between frames. However, with the availability of large RGB-D data captured from depth sensors, learning representations for estimation of scene flow has become possible. This paper introduces a first effort to apply a deep learning method for direct estimation of scene flow by presenting a fully convolutional neural network with an encoder-decoder (ED) architecture. The proposed network SceneEDNet involves estimation of three dimensional motion vectors of all the scene points from sequence of stereo images. The training for direct estimation of scene flow is done using consecutive pairs of stereo images and corresponding scene flow ground truth.

SceneEDNet: A Deep Learning Approach for Scene Flow Estimation

The problem of Scene flow estimation in depth videos has been attracting attention of researchers of robot vision, due to its potential application in various areas of robotics. The conventional scene flow methods are difficult to use in reallife applications due to their long computational overhead. We propose a conditional adversarial network SceneFlowGAN for scene flow estimation. The proposed SceneFlowGAN uses loss function at two ends: both generator and descriptor ends. The proposed network is the first attempt to estimate scene flow using generative adversarial networks, and is able to estimate both the optical flow and disparity from the input stereo images simultaneously. The proposed method is experimented on a large RGB-D benchmark sceneflow dataset.

Ravi Kumar Thakur

Papers

SceneEDNet: A Deep Learning Approach for Scene Flow Estimation

A Conditional Adversarial Network for Scene Flow Estimation

A Conditional Adversarial Network for Scene Flow Estimation