David K. Han

Jeong-gi Kwak, Yuanming Li, Dongsik Yoon et al.

Over the years, 2D GANs have achieved great successes in photorealistic portrait generation. However, they lack 3D understanding in the generation process, thus they suffer from multi-view inconsistency problem. To alleviate the issue, many 3D-aware GANs have been proposed and shown notable results, but 3D GANs struggle with editing semantic attributes. The controllability and interpretability of 3D GANs have not been much explored. In this work, we propose two solutions to overcome these weaknesses of 2D GANs and 3D-aware GANs. We first introduce a novel 3D-aware GAN, SURF-GAN, which is capable of discovering semantic attributes during training and controlling them in an unsupervised manner. After that, we inject the prior of SURF-GAN into StyleGAN to obtain a high-fidelity 3D-controllable generator. Unlike existing latent-based methods allowing implicit pose control, the proposed 3D-controllable StyleGAN enables explicit pose control over portrait generation. This distillation allows direct compatibility between 3D control and many StyleGAN-based techniques (e.g., inversion and stylization), and also brings an advantage in terms of computational resources. Our codes are available at https://github.com/jgkwak95/SURF-GAN.

Dongsik Yoon, Jeong-gi Kwak, Yuanming Li et al.

Image inpainting is an old problem in computer vision that restores occluded regions and completes damaged images. In the case of facial image inpainting, most of the methods generate only one result for each masked image, even though there are other reasonable possibilities. To prevent any potential biases and unnatural constraints stemming from generating only one image, we propose a novel framework for diverse facial inpainting exploiting the embedding space of StyleGAN. Our framework employs pSp encoder and SeFa algorithm to identify semantic components of the StyleGAN embeddings and feed them into our proposed SPARN decoder that adopts region normalization for plausible inpainting. We demonstrate that our proposed method outperforms several state-of-the-art methods.

Jeong-gi Kwak, Yuanming Li, Dongsik Yoon et al.

Recently, synthesizing personalized characters from a single user-given portrait has received remarkable attention as a drastic popularization of social media and the metaverse. The input image is not always in frontal view, thus it is important to acquire or predict canonical view for 3D modeling or other applications. Although the progress of generative models enables the stylization of a portrait, obtaining the stylized image in canonical view is still a challenging task. There have been several studies on face frontalization but their performance significantly decreases when input is not in the real image domain, e.g., cartoon or painting. Stylizing after frontalization also results in degenerated output. In this paper, we propose a novel and unified framework which generates stylized portraits in canonical view. With a proposed latent mapper, we analyze and discover frontalization mapping in a latent space of StyleGAN to stylize and frontalize at once. In addition, our model can be trained with unlabelled 2D image sets, without any 3D supervision. The effectiveness of our method is demonstrated by experimental results.

Dongsik Yoon, Jeonggi Kwak, Yuanming Li et al.

Image inpainting is a technique of completing missing pixels such as occluded region restoration, distracting objects removal, and facial completion. Among these inpainting tasks, facial completion algorithm performs face inpainting according to the user direction. Existing approaches require delicate and well controlled input by the user, thus it is difficult for an average user to provide the guidance sufficiently accurate for the algorithm to generate desired results. To overcome this limitation, we propose an alternative user-guided inpainting architecture that manipulates facial attributes using a single reference image as the guide. Our end-to-end model consists of attribute extractors for accurate reference image attribute transfer and an inpainting model to map the attributes realistically and accurately to generated images. We customize MS-SSIM loss and learnable bidirectional attention maps in which importance structures remain intact even with irregular shaped masks. Based on our evaluation using the publicly available dataset CelebA-HQ, we demonstrate that the proposed method delivers superior performance compared to some state-of-the-art methods specialized in inpainting tasks.

Gwantae Kim, Youngsuk Ryu, Junyeop Lee et al.

In this paper, a deep learning-based model for 3D human motion generation from the text is proposed via gesture action classification and an autoregressive model. The model focuses on generating special gestures that express human thinking, such as waving and nodding. To achieve the goal, the proposed method predicts expression from the sentences using a text classification model based on a pretrained language model and generates gestures using the gate recurrent unit-based autoregressive model. Especially, we proposed the loss for the embedding space for restoring raw motions and generating intermediate motions well. Moreover, the novel data augmentation method and stop token are proposed to generate variable length motions. To evaluate the text classification model and 3D human motion generation model, a gesture action classification dataset and action-based gesture dataset are collected. With several experiments, the proposed method successfully generates perceptually natural and realistic 3D human motion from the text. Moreover, we verified the effectiveness of the proposed method using a public-available action recognition dataset to evaluate cross-dataset generalization performance.

Yuanming Li, Jeong-gi Kwak, David Han et al.

Although manipulating facial attributes by Generative Adversarial Networks (GANs) has been remarkably successful recently, there are still some challenges in explicit control of features such as pose, expression, lighting, etc. Recent methods achieve explicit control over 2D images by combining 2D generative model and 3DMM. However, due to the lack of realism and clarity in texture reconstruction by 3DMM, there is a domain gap between the synthetic image and the rendered image of 3DMM. Since rendered 3DMM images contain facial region only without the background, directly computing the loss between these two domains is not ideal and the resultant trained model will be biased. In this study, we propose to explicitly edit the latent space of the pretrained StyleGAN by controlling the parameters of the 3DMM. To address the domain gap problem, we propose a noval network called 'Map and edit' and a simple but effective attribute editing method to avoid direct loss computation between rendered and synthesized images. Furthermore, since our model can accurately generate multi-view face images while the identity remains unchanged. As a by-product, combined with visibility masks, our proposed model can also generate texture-rich and high-resolution UV facial textures. Our model relies on pretrained StyleGAN, and the proposed model is trained in a self-supervised manner without any manual annotations or datasets.

Diego Patiño, Knut Peterson, Kostas Daniilidis et al.

Implicit shape representation, such as SDFs, is a popular approach to recover the surface of a 3D shape as the level sets of a scalar field. Several methods approximate SDFs using machine learning strategies that exploit the knowledge that SDFs are solutions of the Eikonal partial differential equation (PDEs). In this work, we present a novel approach to surface reconstruction by encoding it as a solution to a proxy PDE, namely Poisson's equation. Then, we explore the connection between Poisson's equation and physics, e.g., the electrostatic potential due to a positive charge density. We employ Green's functions to obtain a closed-form parametric expression for the PDE's solution, and leverage the linearity of our proxy PDE to find the target shape's implicit field as a superposition of solutions. Our method shows improved results in approximating high-frequency details, even with a small number of shape priors.

Amirreza Rouhi, David Han

Teaching machines of scene contextual knowledge would enable them to interact more effectively with the environment and to anticipate or predict objects that may not be immediately apparent in their perceptual field. In this paper, we introduce a novel transformer-based approach called $LMOD$ ( Label-based Missing Object Detection) to teach scene contextual knowledge to machines using an attention mechanism. A distinctive aspect of the proposed approach is its reliance solely on labels from image datasets to teach scene context, entirely eliminating the need for the actual image itself. We show how scene-wide relationships among different objects can be learned using a self-attention mechanism. We further show that the contextual knowledge gained from label based learning can enhance performance of other visual based object detection algorithm.

Amirreza Rouhi, Solmaz Arezoomandan, Knut Peterson et al.

Object detection models typically rely on predefined categories, limiting their ability to identify novel objects in open-world scenarios. To overcome this constraint, we introduce ADAM: Autonomous Discovery and Annotation Model, a training-free, self-refining framework for open-world object labeling. ADAM leverages large language models (LLMs) to generate candidate labels for unknown objects based on contextual information from known entities within a scene. These labels are paired with visual embeddings from CLIP to construct an Embedding-Label Repository (ELR) that enables inference without category supervision. For a newly encountered unknown object, ADAM retrieves visually similar instances from the ELR and applies frequency-based voting and cross-modal re-ranking to assign a robust label. To further enhance consistency, we introduce a self-refinement loop that re-evaluates repository labels using visual cohesion analysis and k-nearest-neighbor-based majority re-labeling. Experimental results on the COCO and PASCAL datasets demonstrate that ADAM effectively annotates novel categories using only visual and contextual signals, without requiring any fine-tuning or retraining.

Seungyeop Lee, Knut Peterson, Solmaz Arezoomandan et al.

A major obstacle to the development of effective monocular depth estimation algorithms is the difficulty in obtaining high-quality depth data that corresponds to collected RGB images. Collecting this data is time-consuming and costly, and even data collected by modern sensors has limited range or resolution, and is subject to inconsistencies and noise. To combat this, we propose a method of data generation in simulation using 3D synthetic environments and CycleGAN domain transfer. We compare this method of data generation to the popular NYUDepth V2 dataset by training a depth estimation model based on the DenseDepth structure using different training sets of real and simulated data. We evaluate the performance of the models on newly collected images and LiDAR depth data from a Husky robot to verify the generalizability of the approach and show that GAN-transformed data can serve as an effective alternative to real-world data, particularly in depth estimation.

Youngsaeng Jin, David K. Han, Hanseok Ko

With the availability of many datasets tailored for autonomous driving in real-world urban scenes, semantic segmentation for urban driving scenes achieves significant progress. However, semantic segmentation for off-road, unstructured environments is not widely studied. Directly applying existing segmentation networks often results in performance degradation as they cannot overcome intrinsic problems in such environments, such as illumination changes. In this paper, a built-in memory module for semantic segmentation is proposed to overcome these problems. The memory module stores significant representations of training images as memory items. In addition to the encoder embedding like items together, the proposed memory module is specifically designed to cluster together instances of the same class even when there are significant variances in embedded features. Therefore, it makes segmentation networks better deal with unexpected illumination changes. A triplet loss is used in training to minimize redundancy in storing discriminative representations of the memory module. The proposed memory module is general so that it can be adopted in a variety of networks. We conduct experiments on the Robot Unstructured Ground Driving (RUGD) dataset and RELLIS dataset, which are collected from off-road, unstructured natural environments. Experimental results show that the proposed memory module improves the performance of existing segmentation networks and contributes to capturing unclear objects over various off-road, unstructured natural scenes with equivalent computational cost and network parameters. As the proposed method can be integrated into compact networks, it presents a viable approach for resource-limited small autonomous platforms.

Youngsaeng Jin, Jonghwan Hong, David Han et al.

Anomaly detection in video streams is a challenging problem because of the scarcity of abnormal events and the difficulty of accurately annotating them. To alleviate these issues, unsupervised learning-based prediction methods have been previously applied. These approaches train the model with only normal events and predict a future frame from a sequence of preceding frames by use of encoder-decoder architectures so that they result in small prediction errors on normal events but large errors on abnormal events. The architecture, however, comes with the computational burden as some anomaly detection tasks require low computational cost without sacrificing performance. In this paper, Cross-Parallel Network (CPNet) for efficient anomaly detection is proposed here to minimize computations without performance drops. It consists of N smaller parallel U-Net, each of which is designed to handle a single input frame, to make the calculations significantly more efficient. Additionally, an inter-network shift module is incorporated to capture temporal relationships among sequential frames to enable more accurate future predictions.The quantitative results show that our model requires less computational cost than the baseline U-Net while delivering equivalent performance in anomaly detection.

Gwantae Kim, David K. Han, Hanseok Ko

A mixed sample data augmentation strategy is proposed to enhance the performance of models on audio scene classification, sound event classification, and speech enhancement tasks. While there have been several augmentation methods shown to be effective in improving image classification performance, their efficacy toward time-frequency domain features of audio is not assured. We propose a novel audio data augmentation approach named "Specmix" specifically designed for dealing with time-frequency domain features. The augmentation method consists of mixing two different data samples by applying time-frequency masks effective in preserving the spectral correlation of each audio sample. Our experiments on acoustic scene classification, sound event classification, and speech enhancement tasks show that the proposed Specmix improves the performance of various neural network architectures by a maximum of 2.7%.

Sangwook Park, David K. Han, Mounya Elhilali

Sound event detection is an important facet of audio tagging that aims to identify sounds of interest and define both the sound category and time boundaries for each sound event in a continuous recording. With advances in deep neural networks, there has been tremendous improvement in the performance of sound event detection systems, although at the expense of costly data collection and labeling efforts. In fact, current state-of-the-art methods employ supervised training methods that leverage large amounts of data samples and corresponding labels in order to facilitate identification of sound category and time stamps of events. As an alternative, the current study proposes a semi-supervised method for generating pseudo-labels from unsupervised data using a student-teacher scheme that balances self-training and cross-training. Additionally, this paper explores post-processing which extracts sound intervals from network prediction, for further improvement in sound event detection performance. The proposed approach is evaluated on sound event detection task for the DCASE2020 challenge. The results of these methods on both "validation" and "public evaluation" sets of DESED database show significant improvement compared to the state-of-the art systems in semi-supervised learning.

Alzahra Badi, Sangwook Park, David K. Han et al.

Performance of learning based Automatic Speech Recognition (ASR) is susceptible to noise, especially when it is introduced in the testing data while not presented in the training data. This work focuses on a feature enhancement for noise robust end-to-end ASR system by introducing a novel variant of denoising autoencoder (DAE). The proposed method uses skip connections in both encoder and decoder sides by passing speech information of the target frame from input to the model. It also uses a new objective function in training model that uses a correlation distance measure in penalty terms by measuring dependency of the latent target features and the model (latent features and enhanced features obtained from the DAE). Performance of the proposed method was compared against a conventional model and a state of the art model under both seen and unseen noisy environments of 7 different types of background noise with different SNR levels (0, 5, 10 and 20 dB). The proposed method also is tested using linear and non-linear penalty terms as well, where, they both show an improvement on the overall average WER under noisy conditions both seen and unseen in comparison to the state-of-the-art model.

Sangwook Park, David K. Han, Hanseok Ko

Simulators that generate observations based on theoretical models can be important tools for development, prediction, and assessment of signal processing algorithms. In order to design these simulators, painstaking effort is required to construct mathematical models according to their application. Complex models are sometimes necessary to represent a variety of real phenomena. In contrast, obtaining synthetic observations from generative models developed from real observations often require much less effort. This paper proposes a generative model based on adversarial learning. Given that observations are typically signals composed of a linear combination of sinusoidal waves and random noises, sinusoidal wave generating networks are first designed based on an adversarial network. Audio waveform generation can then be performed using the proposed network. Several approaches to designing the objective function of the proposed network using adversarial learning are investigated experimentally. In addition, amphibian sound classification is performed using a convolutional neural network trained with real and synthetic sounds. Both qualitative and quantitative results show that the proposed generative model makes realistic signals and is very helpful for data augmentation and data analysis.

Sangwook Park, Seongkyu Mun, Younglo Lee et al.

This paper describes an acoustic scene classification method which achieved the 4th ranking result in the IEEE AASP challenge of Detection and Classification of Acoustic Scenes and Events 2016. In order to accomplish the ensuing task, several methods are explored in three aspects: feature extraction, feature transformation, and score fusion for final decision. In the part of feature extraction, several features are investigated for effective acoustic scene classification. For resolving the issue that the same sound can be heard in different places, a feature transformation is applied for better separation for classification. From these, several systems based on different feature sets are devised for classification. The final result is determined by fusing the individual systems. The method is demonstrated and validated by the experiment conducted using the Challenge database.

Seongkyu Mun, Minkyu Shin, Suwon Shon et al.

Recent acoustic event classification research has focused on training suitable filters to represent acoustic events. However, due to limited availability of target event databases and linearity of conventional filters, there is still room for improving performance. By exploiting the non-linear modeling of deep neural networks (DNNs) and their ability to learn beyond pre-trained environments, this letter proposes a DNN-based feature extraction scheme for the classification of acoustic events. The effectiveness and robustness to noise of the proposed method are demonstrated using a database of indoor surveillance environments.