Normalizing flows, autoregressive models, variational autoencoders (VAEs), and deep energy-based models are among competing likelihood-based frameworks for deep generative learning. Among them, VAEs have the advantage of fast and tractable sampling and easy-to-access encoding networks. However, they are currently outperformed by other models such as normalizing flows and autoregressive models. While the majority of the research in VAEs is focused on the statistical challenges, we explore the orthogonal direction of carefully designing neural architectures for hierarchical VAEs. We propose Nouveau VAE (NVAE), a deep hierarchical VAE built for image generation using depth-wise separable convolutions and batch normalization. NVAE is equipped with a residual parameterization of Normal distributions and its training is stabilized by spectral regularization. We show that NVAE achieves state-of-the-art results among non-autoregressive likelihood-based models on the MNIST, CIFAR-10, and CelebA HQ datasets and it provides a strong baseline on FFHQ. For example, on CIFAR-10, NVAE pushes the state-of-the-art from 2.98 to 2.91 bits per dimension, and it produces high-quality images on CelebA HQ as shown in Fig. 1. To the best of our knowledge, NVAE is the first successful VAE applied to natural images as large as 256$\times$256 pixels.
Phrase grounding, the problem of associating image regions to caption words, is a crucial component of vision-language tasks. We show that phrase grounding can be learned by optimizing word-region attention to maximize a lower bound on mutual information between images and caption words. Given pairs of images and captions, we maximize compatibility of the attention-weighted regions and the words in the corresponding caption, compared to non-corresponding pairs of images and captions. A key idea is to construct effective negative captions for learning through language model guided word substitutions. Training with our negatives yields a $\sim10\%$ absolute gain in accuracy over randomly-sampled negatives from the training data. Our weakly supervised phrase grounding model trained on COCO-Captions shows a healthy gain of $5.7\%$ to achieve $76.7\%$ accuracy on Flickr30K Entities benchmark.
Stereo-based depth estimation is a cornerstone of computer vision, with state-of-the-art methods delivering accurate results in real time. For several applications such as autonomous navigation, however, it may be useful to trade accuracy for lower latency. We present Bi3D, a method that estimates depth via a series of binary classifications. Rather than testing if objects are at a particular depth $D$, as existing stereo methods do, it classifies them as being closer or farther than $D$. This property offers a powerful mechanism to balance accuracy and latency. Given a strict time budget, Bi3D can detect objects closer than a given distance in as little as a few milliseconds, or estimate depth with arbitrarily coarse quantization, with complexity linear with the number of quantization levels. Bi3D can also use the allotted quantization levels to get continuous depth, but in a specific depth range. For standard stereo (i.e., continuous depth on the whole range), our method is close to or on par with state-of-the-art, finely tuned stereo methods.
One fundamental difficulty in robotic learning is the sim-real gap problem. In this work, we propose to use segmentation as the interface between perception and control, as a domain-invariant state representation. We identify two sources of sim-real gap, one is dynamics sim-real gap, the other is visual sim-real gap. To close dynamics sim-real gap, we propose to use closed-loop control. For complex task with segmentation mask input, we further propose to learn a closed-loop model-free control policy with deep neural network using imitation learning. To close visual sim-real gap, we propose to learn a perception model in real environment using simulated target plus real background image, without using any real world supervision. We demonstrate this methodology in eye-in-hand grasping task. We train a closed-loop control policy model that taking the segmentation as input using simulation. We show that this control policy is able to transfer from simulation to real environment. The closed-loop control policy is not only robust with respect to discrepancies between the dynamic model of the simulated and real robot, but also is able to generalize to unseen scenarios where the target is moving and even learns to recover from failures. We train the perception segmentation model using training data generated by composing real background images with simulated images of the target. Combining the control policy learned from simulation with the perception model, we achieve an impressive $\bf{88\%}$ success rate in grasping a tiny sphere with a real robot.
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to focus on discriminative parts rather than entire objects; (3) without ground truth, object proposals have to be redundant for high recalls, causing significant memory consumption. Addressing these challenges is difficult, as it often requires to eliminate uncertainties and trivial solutions. To target these issues we develop an instance-aware and context-focused unified framework. It employs an instance-aware self-training algorithm and a learnable Concrete DropBlock while devising a memory-efficient sequential batch back-propagation. Our proposed method achieves state-of-the-art results on COCO ($12.1\% ~AP$, $24.8\% ~AP_{50}$), VOC 2007 ($54.9\% ~AP$), and VOC 2012 ($52.1\% ~AP$), improving baselines by great margins. In addition, the proposed method is the first to benchmark ResNet based models and weakly supervised video object detection. Refer to our project page for code, models, and more details: https://github.com/NVlabs/wetectron.
Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets. However, manually labeling viewpoints is notoriously hard, error-prone, and time-consuming. On the other hand, it is relatively easy to mine many unlabelled images of an object category from the internet, e.g., of cars or faces. We seek to answer the research question of whether such unlabeled collections of in-the-wild images can be successfully utilized to train viewpoint estimation networks for general object categories purely via self-supervision. Self-supervision here refers to the fact that the only true supervisory signal that the network has is the input image itself. We propose a novel learning framework which incorporates an analysis-by-synthesis paradigm to reconstruct images in a viewpoint aware manner with a generative network, along with symmetry and adversarial constraints to successfully supervise our viewpoint estimation network. We show that our approach performs competitively to fully-supervised approaches for several object categories like human faces, cars, buses, and trains. Our work opens up further research in self-supervised viewpoint learning and serves as a robust baseline for it. We open-source our code at https://github.com/NVlabs/SSV.
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.
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.
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.