Models, code, and papers for "Jan Kautz":
To denoise a reference patch, the Non-Local-Means denoising filter processes a set of neighbor patches. Few Nearest Neighbors (NN) are used to limit the computational burden of the algorithm. Here here we show analytically that the NN approach introduces a bias in the denoised patch, and we propose a different neighbors' collection criterion, named Statistical NN (SNN), to alleviate this issue. Our approach outperforms the traditional one in case of both white and colored noise: fewer SNNs generate images of higher quality, at a lower computational cost.
We present an iterative overlap estimation technique to augment existing point cloud registration algorithms that can achieve high performance in difficult real-world situations where large pose displacement and non-overlapping geometry would otherwise cause traditional methods to fail. Our approach estimates overlapping regions through an iterative Expectation Maximization procedure that encodes the sensor field-of-view into the registration process. The proposed technique, Expected Overlap Estimation (EOE), is derived from the observation that differences in field-of-view violate the iid assumption implicitly held by all maximum likelihood based registration techniques. We demonstrate how our approach can augment many popular registration methods with minimal computational overhead. Through experimentation on both synthetic and real-world datasets, we find that adding an explicit overlap estimation step can aid robust outlier handling and increase the accuracy of both ICP-based and GMM-based registration methods, especially in large unstructured domains and where the amount of overlap between point clouds is very small.
Point cloud registration sits at the core of many important and challenging 3D perception problems including autonomous navigation, SLAM, object/scene recognition, and augmented reality. In this paper, we present a new registration algorithm that is able to achieve state-of-the-art speed and accuracy through its use of a hierarchical Gaussian Mixture Model (GMM) representation. Our method constructs a top-down multi-scale representation of point cloud data by recursively running many small-scale data likelihood segmentations in parallel on a GPU. We leverage the resulting representation using a novel PCA-based optimization criterion that adaptively finds the best scale to perform data association between spatial subsets of point cloud data. Compared to previous Iterative Closest Point and GMM-based techniques, our tree-based point association algorithm performs data association in logarithmic-time while dynamically adjusting the level of detail to best match the complexity and spatial distribution characteristics of local scene geometry. In addition, unlike other GMM methods that restrict covariances to be isotropic, our new PCA-based optimization criterion well-approximates the true MLE solution even when fully anisotropic Gaussian covariances are used. Efficient data association, multi-scale adaptability, and a robust MLE approximation produce an algorithm that is up to an order of magnitude both faster and more accurate than current state-of-the-art on a wide variety of 3D datasets captured from LiDAR to structured light.
The non-stationary nature of image characteristics calls for adaptive processing, based on the local image content. We propose a simple and flexible method to learn local tuning of parameters in adaptive image processing: we extract simple local features from an image and learn the relation between these features and the optimal filtering parameters. Learning is performed by optimizing a user defined cost function (any image quality metric) on a training set. We apply our method to three classical problems (denoising, demosaicing and deblurring) and we show the effectiveness of the learned parameter modulation strategies. We also show that these strategies are consistent with theoretical results from the literature.
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions. To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs. We compare the proposed framework with competing approaches and present high quality image translation results on various challenging unsupervised image translation tasks, including street scene image translation, animal image translation, and face image translation. We also apply the proposed framework to domain adaptation and achieve state-of-the-art performance on benchmark datasets. Code and additional results are available in https://github.com/mingyuliutw/unit .
Unconstrained remote gaze tracking using off-the-shelf cameras is a challenging problem. Recently, promising algorithms for appearance-based gaze estimation using convolutional neural networks (CNN) have been proposed. Improving their robustness to various confounding factors including variable head pose, subject identity, illumination and image quality remain open problems. In this work, we study the effect of variable head pose on machine learning regressors trained to estimate gaze direction. We propose a novel branched CNN architecture that improves the robustness of gaze classifiers to variable head pose, without increasing computational cost. We also present various procedures to effectively train our gaze network including transfer learning from the more closely related task of object viewpoint estimation and from a large high-fidelity synthetic gaze dataset, which enable our ten times faster gaze network to achieve competitive accuracy to its current state-of-the-art direct competitor.
The reflections caused by common semi-reflectors, such as glass windows, can impact the performance of computer vision algorithms. State-of-the-art methods can remove reflections on synthetic data and in controlled scenarios. However, they are based on strong assumptions and do not generalize well to real-world images. Contrary to a common misconception, real-world images are challenging even when polarization information is used. We present a deep learning approach to separate the reflected and the transmitted components of the recorded irradiance, which explicitly uses the polarization properties of light. To train it, we introduce an accurate synthetic data generation pipeline, which simulates realistic reflections, including those generated by curved and non-ideal surfaces, non-static scenes, and high-dynamic-range scenes.
In this paper, we address the challenging problem of efficient temporal activity detection in untrimmed long videos. While most recent work has focused and advanced the detection accuracy, the inference time can take seconds to minutes in processing each single video, which is too slow to be useful in real-world settings. This motivates the proposed budget-aware framework, which learns to perform activity detection by intelligently selecting a small subset of frames according to a specified time budget. We formulate this problem as a Markov decision process, and adopt a recurrent network to model the frame selection policy. We derive a recurrent policy gradient based approach to approximate the gradient of the non-decomposable and non-differentiable objective defined in our problem. In the extensive experiments, we achieve competitive detection accuracy, and more importantly, our approach is able to substantially reduce computation time and detect multiple activities with only 0.35s for each untrimmed long video.
Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems. The impact of the loss layer of neural networks, however, has not received much attention in the context of image processing: the default and virtually only choice is L2. In this paper, we bring attention to alternative choices for image restoration. In particular, we show the importance of perceptually-motivated losses when the resulting image is to be evaluated by a human observer. We compare the performance of several losses, and propose a novel, differentiable error function. We show that the quality of the results improves significantly with better loss functions, even when the network architecture is left unchanged.
In the context of deep learning for robotics, we show effective method of training a real robot to grasp a tiny sphere (1.37cm of diameter), with an original combination of system design choices. We decompose the end-to-end system into a vision module and a closed-loop controller module. The two modules use target object segmentation as their common interface. The vision module extracts information from the robot end-effector camera, in the form of a binary segmentation mask of the target. We train it to achieve effective domain transfer by composing real background images with simulated images of the target. The controller module takes as input the binary segmentation mask, and thus is agnostic to visual discrepancies between simulated and real environments. We train our closed-loop controller in simulation using imitation learning and show it is robust with respect to discrepancies between the dynamic model of the simulated and real robot: when combined with eye-in-hand observations, we achieve a 90% success rate in grasping a tiny sphere with a real robot. The controller can generalize to unseen scenarios where the target is moving and even learns to recover from failures.
Power consumption is a critical factor for the deployment of embedded computer vision systems. We explore the use of computational cameras that directly output binary gradient images to reduce the portion of the power consumption allocated to image sensing. We survey the accuracy of binary gradient cameras on a number of computer vision tasks using deep learning. These include object recognition, head pose regression, face detection, and gesture recognition. We show that, for certain applications, accuracy can be on par or even better than what can be achieved on traditional images. We are also the first to recover intensity information from binary spatial gradient images--useful for applications with a human observer in the loop, such as surveillance. Our results, which we validate with a prototype binary gradient camera, point to the potential of gradient-based computer vision systems.
We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training. First, we design a compact but effective CNN model, called PWC-Net, according to simple and well-established principles: pyramidal processing, warping, and cost volume processing. PWC-Net is 17 times smaller in size, 2 times faster in inference, and 11\% more accurate on Sintel final than the recent FlowNet2 model. It is the winning entry in the optical flow competition of the robust vision challenge. Next, we experimentally analyze the sources of our performance gains. In particular, we use the same training procedure of PWC-Net to retrain FlowNetC, a sub-network of FlowNet2. The retrained FlowNetC is 56\% more accurate on Sintel final than the previously trained one and even 5\% more accurate than the FlowNet2 model. We further improve the training procedure and increase the accuracy of PWC-Net on Sintel by 10\% and on KITTI 2012 and 2015 by 20\%. Our newly trained model parameters and training protocols will be available on https://github.com/NVlabs/PWC-Net
Unsupervised image-to-image translation is an important and challenging problem in computer vision. Given an image in the source domain, the goal is to learn the conditional distribution of corresponding images in the target domain, without seeing any pairs of corresponding images. While this conditional distribution is inherently multimodal, existing approaches make an overly simplified assumption, modeling it as a deterministic one-to-one mapping. As a result, they fail to generate diverse outputs from a given source domain image. To address this limitation, we propose a Multimodal Unsupervised Image-to-image Translation (MUNIT) framework. We assume that the image representation can be decomposed into a content code that is domain-invariant, and a style code that captures domain-specific properties. To translate an image to another domain, we recombine its content code with a random style code sampled from the style space of the target domain. We analyze the proposed framework and establish several theoretical results. Extensive experiments with comparisons to the state-of-the-art approaches further demonstrates the advantage of the proposed framework. Moreover, our framework allows users to control the style of translation outputs by providing an example style image. Code and pretrained models are available at https://github.com/nvlabs/MUNIT
Given a random pair of images, an arbitrary style transfer method extracts the feel from the reference image to synthesize an output based on the look of the other content image. Recent arbitrary style transfer methods transfer second order statistics from reference image onto content image via a multiplication between content image features and a transformation matrix, which is computed from features with a pre-determined algorithm. These algorithms either require computationally expensive operations, or fail to model the feature covariance and produce artifacts in synthesized images. Generalized from these methods, in this work, we derive the form of transformation matrix theoretically and present an arbitrary style transfer approach that learns the transformation matrix with a feed-forward network. Our algorithm is highly efficient yet allows a flexible combination of multi-level styles while preserving content affinity during style transfer process. We demonstrate the effectiveness of our approach on four tasks: artistic style transfer, video and photo-realistic style transfer as well as domain adaptation, including comparisons with the state-of-the-art methods.
We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the cur- rent optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, it outperforms all published optical flow methods on the MPI Sintel final pass and KITTI 2015 benchmarks, running at about 35 fps on Sintel resolution (1024x436) images. Our models are available on https://github.com/NVlabs/PWC-Net.
Visual signals in a video can be divided into content and motion. While content specifies which objects are in the video, motion describes their dynamics. Based on this prior, we propose the Motion and Content decomposed Generative Adversarial Network (MoCoGAN) framework for video generation. The proposed framework generates a video by mapping a sequence of random vectors to a sequence of video frames. Each random vector consists of a content part and a motion part. While the content part is kept fixed, the motion part is realized as a stochastic process. To learn motion and content decomposition in an unsupervised manner, we introduce a novel adversarial learning scheme utilizing both image and video discriminators. Extensive experimental results on several challenging datasets with qualitative and quantitative comparison to the state-of-the-art approaches, verify effectiveness of the proposed framework. In addition, we show that MoCoGAN allows one to generate videos with same content but different motion as well as videos with different content and same motion.
Given two consecutive frames from a pair of stereo cameras, 3D scene flow methods simultaneously estimate the 3D geometry and motion of the observed scene. Many existing approaches use superpixels for regularization, but may predict inconsistent shapes and motions inside rigidly moving objects. We instead assume that scenes consist of foreground objects rigidly moving in front of a static background, and use semantic cues to produce pixel-accurate scene flow estimates. Our cascaded classification framework accurately models 3D scenes by iteratively refining semantic segmentation masks, stereo correspondences, 3D rigid motion estimates, and optical flow fields. We evaluate our method on the challenging KITTI autonomous driving benchmark, and show that accounting for the motion of segmented vehicles leads to state-of-the-art performance.
Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the first and second-order Taylor expansions to approximate a filter's contribution. Both methods scale consistently across any network layer without requiring per-layer sensitivity analysis and can be applied to any kind of layer, including skip connections. For modern networks trained on ImageNet, we measured experimentally a high (>93%) correlation between the contribution computed by our methods and a reliable estimate of the true importance. Pruning with the proposed methods leads to an improvement over state-of-the-art in terms of accuracy, FLOPs, and parameter reduction. On ResNet-101, we achieve a 40% FLOPS reduction by removing 30% of the parameters, with a loss of 0.02% in the top-1 accuracy on ImageNet. Code is available at https://github.com/NVlabs/Taylor_pruning.
Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the invariance to input changes. The generative pipelines in existing methods, however, stay relatively separate from the discriminative re-id learning stages. Accordingly, re-id models are often trained in a straightforward manner on the generated data. In this paper, we seek to improve learned re-id embeddings by better leveraging the generated data. To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end. Our model involves a generative module that separately encodes each person into an appearance code and a structure code, and a discriminative module that shares the appearance encoder with the generative module. By switching the appearance or structure codes, the generative module is able to generate high-quality cross-id composed images, which are online fed back to the appearance encoder and used to improve the discriminative module. The proposed joint learning framework renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets.