Recent research has shown remarkable success in revealing "steering" directions in the latent spaces of pre-trained GANs. These directions correspond to semantically meaningful image transformations e.g., shift, zoom, color manipulations), and have similar interpretable effects across all categories that the GAN can generate. Some methods focus on user-specified transformations, while others discover transformations in an unsupervised manner. However, all existing techniques rely on an optimization procedure to expose those directions, and offer no control over the degree of allowed interaction between different transformations. In this paper, we show that "steering" trajectories can be computed in closed form directly from the generator's weights without any form of training or optimization. This applies to user-prescribed geometric transformations, as well as to unsupervised discovery of more complex effects. Our approach allows determining both linear and nonlinear trajectories, and has many advantages over previous methods. In particular, we can control whether one transformation is allowed to come on the expense of another (e.g. zoom-in with or without allowing translation to keep the object centered). Moreover, we can determine the natural end-point of the trajectory, which corresponds to the largest extent to which a transformation can be applied without incurring degradation. Finally, we show how transferring attributes between images can be achieved without optimization, even across different categories.
We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severe missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel object categories.
We present an approach for estimating surface normals from in-the-wild color images of faces. While data-driven strategies have been proposed for single face images, limited available ground truth data makes this problem difficult. To alleviate this issue, we propose a method that can leverage all available image and normal data, whether paired or not, thanks to a novel cross-modal learning architecture. In particular, we enable additional training with single modality data, either color or normal, by using two encoder-decoder networks with a shared latent space. The proposed architecture also enables face details to be transferred between the image and normal domains, given paired data, through skip connections between the image encoder and normal decoder. Core to our approach is a novel module that we call deactivable skip connections, which allows integrating both the auto-encoded and image-to-normal branches within the same architecture that can be trained end-to-end. This allows learning of a rich latent space that can accurately capture the normal information. We compare against state-of-the-art methods and show that our approach can achieve significant improvements, both quantitative and qualitative, with natural face images.
Learning interpretable and interpolatable latent representations has been an emerging research direction, allowing researchers to understand and utilize the derived latent space for further applications such as visual synthesis or recognition. While most existing approaches derive an interpolatable latent space and induces smooth transition in image appearance, it is still not clear how to observe desirable representations which would contain semantic information of interest. In this paper, we aim to learn meaningful representations and simultaneously perform semantic-oriented and visually-smooth interpolation. To this end, we propose an angular triplet-neighbor loss (ATNL) that enables learning a latent representation whose distribution matches the semantic information of interest. With the latent space guided by ATNL, we further utilize spherical semantic interpolation for generating semantic warping of images, allowing synthesis of desirable visual data. Experiments on MNIST and CMU Multi-PIE datasets qualitatively and quantitatively verify the effectiveness of our method.
Text-based person re-identification(Re-id) is an important task in video surveillance, which consists of retrieving the corresponding person's image given a textual description from a large gallery of images. It is difficult to directly match visual contents with the textual descriptions due to the modality heterogeneity. On the one hand, the textual embeddings are not discriminative enough, which originates from the high abstraction of the textual descriptions. One the other hand,Global average pooling (GAP) is commonly utilized to extract more general or smoothed features implicitly but ignores salient local features, which are more important for the cross-modal matching problem. With that in mind, a novel Dual-path CNN with Max Gated block (DCMG) is proposed to extract discriminative word embeddings and make visual-textual association concern more on remarkable features of both modalities. The proposed framework is based on two deep residual CNNs jointly optimized with cross-modal projection matching (CMPM) loss and cross-modal projection classification (CMPC) loss to embed the two modalities into a joint feature space. First, the pre-trained language model, BERT, is combined with the convolutional neural network (CNN) to learn better word embeddings in the text-to-image matching domain. Second, the global Max pooling (GMP) layer is applied to make the visual-textual features focus more on the salient part. To further alleviate the noise of the maxed-pooled features, the gated block (GB) is proposed to produce an attention map that focuses on meaningful features of both modalities. Finally, extensive experiments are conducted on the benchmark dataset, CUHK-PEDES, in which our approach achieves the rank-1 score of 55.81% and outperforms the state-of-the-art method by 1.3%.
Selecting the most suitable local invariant feature detector for a particular application has rendered the task of evaluating feature detectors a critical issue in vision research. No state-of-the-art image feature detector works satisfactorily under all types of image transformations. Although the literature offers a variety of comparison works focusing on performance evaluation of image feature detectors under several types of image transformation, the influence of the scene content on the performance of local feature detectors has received little attention so far. This paper aims to bridge this gap with a new framework for determining the type of scenes, which maximize and minimize the performance of detectors in terms of repeatability rate. Several state-of-the-art feature detectors have been assessed utilizing a large database of 12936 images generated by applying uniform light and blur changes to 539 scenes captured from the real world. The results obtained provide new insights into the behaviour of feature detectors.
In this paper, we present a combined architecture using dilated and transposed convolutional neural networks for accurate and efficient semantic image segmentation. In contrast to previous fully convolutional neural networks such as FCN with almost all computation shared on the entire image, we propose an additional architecture which we have named as dilated - transposed fully convolutional neural networks. To achieve this goal, we used dilated convolutional layers in downsampling and transposed convolutional layers in upsampling layers. We have used skip connections in between the blocks formed by convolutions and max pooling layers. This type of architecture has been used successfully in the past for image classification using residual network. In addition we also found selu activation function instead of relu to give better results on the test set images. We reason this is the due to avoiding the model getting stuck in a local minimum, thus experiencing a famous vanishing gradient problem in case with relu activation function. Meanwhile, our result achieved pixel wise class accuracy of 88% on the test set and mean Intersection Over Union(IOU) value of 53.5 which is better than the state of the art using the previous fully convolutional neural networks.
Automatic supervised classification of satellite images with complex modelling such as deep neural networks requires the availability of representative training datasets. While there exists a plethora of datasets that can be used for this purpose, they are usually very heterogeneous and not interoperable. This prevents the combination of two or more training datasets for improving image classification tasks based on machine learning. To alleviate these problems, we propose a methodology for structuring and harmonising open training datasets on the basis of a series of fundamental attributes we put forward for any such dataset. By applying this methodology to seven representative open training datasets, we generate a harmonised collection called SatImNet. Its usefulness is demonstrated for enhanced satellite image classification and segmentation based on convolutional neural networks. Data and open source code are provided to ensure the reproducibility of all obtained results and facilitate the ingestion of additional datasets in SatImNet.
This work aims to address the problem of image-based question-answering (QA) with new models and datasets. In our work, we propose to use neural networks and visual semantic embeddings, without intermediate stages such as object detection and image segmentation, to predict answers to simple questions about images. Our model performs 1.8 times better than the only published results on an existing image QA dataset. We also present a question generation algorithm that converts image descriptions, which are widely available, into QA form. We used this algorithm to produce an order-of-magnitude larger dataset, with more evenly distributed answers. A suite of baseline results on this new dataset are also presented.
The goal of perception for autonomous vehicles is to extract semantic representations from multiple sensors and fuse these representations into a single "bird's-eye-view" coordinate frame for consumption by motion planning. We propose a new end-to-end architecture that directly extracts a bird's-eye-view representation of a scene given image data from an arbitrary number of cameras. The core idea behind our approach is to "lift" each image individually into a frustum of features for each camera, then "splat" all frustums into a rasterized bird's-eye-view grid. By training on the entire camera rig, we provide evidence that our model is able to learn not only how to represent images but how to fuse predictions from all cameras into a single cohesive representation of the scene while being robust to calibration error. On standard bird's-eye-view tasks such as object segmentation and map segmentation, our model outperforms all baselines and prior work. In pursuit of the goal of learning dense representations for motion planning, we show that the representations inferred by our model enable interpretable end-to-end motion planning by "shooting" template trajectories into a bird's-eye-view cost map output by our network. We benchmark our approach against models that use oracle depth from lidar. Project page with code: https://nv-tlabs.github.io/lift-splat-shoot .