What comprises a good talking-head video generation?: A Survey and Benchmark

Over the years, performance evaluation has become essential in computer vision, enabling tangible progress in many sub-fields. While talking-head video generation has become an emerging research topic, existing evaluations on this topic present many limitations. For example, most approaches use human subjects (e.g., via Amazon MTurk) to evaluate their research claims directly. This subjective evaluation is cumbersome, unreproducible, and may impend the evolution of new research. In this work, we present a carefully-designed benchmark for evaluating talking-head video generation with standardized dataset pre-processing strategies. As for evaluation, we either propose new metrics or select the most appropriate ones to evaluate results in what we consider as desired properties for a good talking-head video, namely, identity preserving, lip synchronization, high video quality, and natural-spontaneous motion. By conducting a thoughtful analysis across several state-of-the-art talking-head generation approaches, we aim to uncover the merits and drawbacks of current methods and point out promising directions for future work. All the evaluation code is available at: https://github.com/lelechen63/talking-head-generation-survey.

Learning a Weakly-Supervised Video Actor-Action Segmentation Model with a Wise Selection

We address weakly-supervised video actor-action segmentation (VAAS), which extends general video object segmentation (VOS) to additionally consider action labels of the actors. The most successful methods on VOS synthesize a pool of pseudo-annotations (PAs) and then refine them iteratively. However, they face challenges as to how to select from a massive amount of PAs high-quality ones, how to set an appropriate stop condition for weakly-supervised training, and how to initialize PAs pertaining to VAAS. To overcome these challenges, we propose a general Weakly-Supervised framework with a Wise Selection of training samples and model evaluation criterion (WS^2). Instead of blindly trusting quality-inconsistent PAs, WS^2 employs a learning-based selection to select effective PAs and a novel region integrity criterion as a stopping condition for weakly-supervised training. In addition, a 3D-Conv GCAM is devised to adapt to the VAAS task. Extensive experiments show that WS^2 achieves state-of-the-art performance on both weakly-supervised VOS and VAAS tasks and is on par with the best fully-supervised method on VAAS.

Deep Grouping Model for Unified Perceptual Parsing

The perceptual-based grouping process produces a hierarchical and compositional image representation that helps both human and machine vision systems recognize heterogeneous visual concepts. Examples can be found in the classical hierarchical superpixel segmentation or image parsing works. However, the grouping process is largely overlooked in modern CNN-based image segmentation networks due to many challenges, including the inherent incompatibility between the grid-shaped CNN feature map and the irregular-shaped perceptual grouping hierarchy. Overcoming these challenges, we propose a deep grouping model (DGM) that tightly marries the two types of representations and defines a bottom-up and a top-down process for feature exchanging. When evaluating the model on the recent Broden+ dataset for the unified perceptual parsing task, it achieves state-of-the-art results while having a small computational overhead compared to other contextual-based segmentation models. Furthermore, the DGM has better interpretability compared with modern CNN methods.

Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution

In this paper, we explore the space-time video super-resolution task, which aims to generate a high-resolution (HR) slow-motion video from a low frame rate (LFR), low-resolution (LR) video. A simple solution is to split it into two sub-tasks: video frame interpolation (VFI) and video super-resolution (VSR). However, temporal interpolation and spatial super-resolution are intra-related in this task. Two-stage methods cannot fully take advantage of the natural property. In addition, state-of-the-art VFI or VSR networks require a large frame-synthesis or reconstruction module for predicting high-quality video frames, which makes the two-stage methods have large model sizes and thus be time-consuming. To overcome the problems, we propose a one-stage space-time video super-resolution framework, which directly synthesizes an HR slow-motion video from an LFR, LR video. Rather than synthesizing missing LR video frames as VFI networks do, we firstly temporally interpolate LR frame features in missing LR video frames capturing local temporal contexts by the proposed feature temporal interpolation network. Then, we propose a deformable ConvLSTM to align and aggregate temporal information simultaneously for better leveraging global temporal contexts. Finally, a deep reconstruction network is adopted to predict HR slow-motion video frames. Extensive experiments on benchmark datasets demonstrate that the proposed method not only achieves better quantitative and qualitative performance but also is more than three times faster than recent two-stage state-of-the-art methods, e.g., DAIN+EDVR and DAIN+RBPN.

Assembling Semantically-Disentangled Representations for Predictive-Generative Models via Adaptation from Synthetic Domain

Deep neural networks can form high-level hierarchical representations of input data. Various researchers have demonstrated that these representations can be used to enable a variety of useful applications. However, such representations are typically based on the statistics within the data, and may not conform with the semantic representation that may be necessitated by the application. Conditional models are typically used to overcome this challenge, but they require large annotated datasets which are difficult to come by and costly to create. In this paper, we show that semantically-aligned representations can be generated instead with the help of a physics based engine. This is accomplished by creating a synthetic dataset with decoupled attributes, learning an encoder for the synthetic dataset, and augmenting prescribed attributes from the synthetic domain with attributes from the real domain. It is shown that the proposed (SYNTH-VAE-GAN) method can construct a conditional predictive-generative model of human face attributes without relying on real data labels.

TailorGAN: Making User-Defined Fashion Designs

Attribute editing has become an important and emerging topic of computer vision. In this paper, we consider a task: given a reference garment image A and another image B with target attribute (collar/sleeve), generate a photo-realistic image which combines the texture from reference A and the new attribute from reference B. The highly convoluted attributes and the lack of paired data are the main challenges to the task. To overcome those limitations, we propose a novel self-supervised model to synthesize garment images with disentangled attributes (e.g., collar and sleeves) without paired data. Our method consists of a reconstruction learning step and an adversarial learning step. The model learns texture and location information through reconstruction learning. And, the model's capability is generalized to achieve single-attribute manipulation by adversarial learning. Meanwhile, we compose a new dataset, named GarmentSet, with annotation of landmarks of collars and sleeves on clean garment images. Extensive experiments on this dataset and real-world samples demonstrate that our method can synthesize much better results than the state-of-the-art methods in both quantitative and qualitative comparisons.

Deep Audio Prior

Deep convolutional neural networks are known to specialize in distilling compact and robust prior from a large amount of data. We are interested in applying deep networks in the absence of training dataset. In this paper, we introduce deep audio prior (DAP) which leverages the structure of a network and the temporal information in a single audio file. Specifically, we demonstrate that a randomly-initialized neural network can be used with carefully designed audio prior to tackle challenging audio problems such as universal blind source separation, interactive audio editing, audio texture synthesis, and audio co-separation. To understand the robustness of the deep audio prior, we construct a benchmark dataset \emph{Universal-150} for universal sound source separation with a diverse set of sources. We show superior audio results than previous work on both qualitative and quantitative evaluations. We also perform thorough ablation study to validate our design choices.

Learning from Interventions using Hierarchical Policies for Safe Learning

Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert's reaction time and only learns short-term behavior. We address these limitations by 1) interpolating the expert's interventions back in time, and 2) by splitting the policy into two hierarchical levels, one that generates sub-goals for the future and another that generates actions to reach those desired sub-goals. This sub-goal prediction forces the algorithm to learn long-term behavior while also being robust to the expert's reaction time. Our experiments show that LfI using sub-goals in a hierarchical policy framework trains faster and achieves better asymptotic performance than typical LfD.

Weakly Supervised Object Localization with Inter-Intra Regulated CAMs

Weakly supervised object localization (WSOL) aims to locate objects in images by learning only from image-level labels. Current methods are trying to obtain localization results relying on Class Activation Maps (CAMs). Usually, they propose additional CAMs or feature maps generated from internal layers of deep networks to encourage different CAMs to be either \textbf{adversarial} or \textbf{cooperated} with each other. In this work, instead of following one of the two main approaches before, we analyze their internal relationship and propose a novel intra-sample strategy which regulates two CAMs of the same sample, generated from different classifiers, to dynamically adapt each of their pixels involved in adversarial or cooperative process based on their own values. We mathematically demonstrate that our approach is a more general version of the current state-of-the-art method with less hyper-parameters. Besides, we further develop an inter-sample criterion module for our WSOL task, which is originally proposed in co-segmentation problems, to refine generated CAMs of each sample. The module considers a subgroup of samples under the same category and regulates their object regions. With experiment on two widely-used datasets, we show that our proposed method significantly outperforms existing state-of-the-art, setting a new record for weakly-supervised object localization.