Dogucan Yaman

Fevziye Irem Eyiokur, Dogucan Yaman, Hazım Kemal Ekenel et al.

Exposure errors in an image cause a degradation in the contrast and low visibility in the content. In this paper, we address this problem and propose an end-to-end exposure correction model in order to handle both under- and overexposure errors with a single model. Our model contains an image encoder, consecutive residual blocks, and image decoder to synthesize the corrected image. We utilize perceptual loss, feature matching loss, and multi-scale discriminator to increase the quality of the generated image as well as to make the training more stable. The experimental results indicate the effectiveness of proposed model. We achieve the state-of-the-art result on a large-scale exposure dataset. Besides, we investigate the effect of exposure setting of the image on the portrait matting task. We find that under- and overexposed images cause severe degradation in the performance of the portrait matting models. We show that after applying exposure correction with the proposed model, the portrait matting quality increases significantly. https://github.com/yamand16/ExposureCorrection

Alexander Waibel, Moritz Behr, Fevziye Irem Eyiokur et al.

In this paper, we propose a neural end-to-end system for voice preserving, lip-synchronous translation of videos. The system is designed to combine multiple component models and produces a video of the original speaker speaking in the target language that is lip-synchronous with the target speech, yet maintains emphases in speech, voice characteristics, face video of the original speaker. The pipeline starts with automatic speech recognition including emphasis detection, followed by a translation model. The translated text is then synthesized by a Text-to-Speech model that recreates the original emphases mapped from the original sentence. The resulting synthetic voice is then mapped back to the original speakers' voice using a voice conversion model. Finally, to synchronize the lips of the speaker with the translated audio, a conditional generative adversarial network-based model generates frames of adapted lip movements with respect to the input face image as well as the output of the voice conversion model. In the end, the system combines the generated video with the converted audio to produce the final output. The result is a video of a speaker speaking in another language without actually knowing it. To evaluate our design, we present a user study of the complete system as well as separate evaluations of the single components. Since there is no available dataset to evaluate our whole system, we collect a test set and evaluate our system on this test set. The results indicate that our system is able to generate convincing videos of the original speaker speaking the target language while preserving the original speaker's characteristics. The collected dataset will be shared.

Dogucan Yaman, Fevziye Irem Eyiokur, Leonard Bärmann et al.

Talking face generation aims to create realistic videos with accurate lip synchronization and high visual quality, using given audio and reference video while preserving identity and visual characteristics. In this paper, we start by identifying several issues with existing synchronization learning methods. These involve unstable training, lip synchronization, and visual quality issues caused by lip-sync loss, SyncNet, and lip leaking from the identity reference. To address these issues, we first tackle the lip leaking problem by introducing a silent-lip generator, which changes the lips of the identity reference to alleviate leakage. We then introduce stabilized synchronization loss and AVSyncNet to overcome problems caused by lip-sync loss and SyncNet. Experiments show that our model outperforms state-of-the-art methods in both visual quality and lip synchronization. Comprehensive ablation studies further validate our individual contributions and their cohesive effects.

Dogucan Yaman, Fevziye Irem Eyiokur, Hazım Kemal Ekenel et al.

Inpainting-based talking face generation aims to preserve video details such as pose, lighting, and gestures while modifying only lip motion, often using an identity reference image to maintain speaker consistency. However, this mechanism can introduce lip leaking, where generated lips are influenced by the reference image rather than solely by the driving audio. Such leakage is difficult to detect with standard metrics and conventional test setup. To address this, we propose a systematic evaluation methodology to analyze and quantify lip leakage. Our framework employs three complementary test setups: silent-input generation, mismatched audio-video pairing, and matched audio-video synthesis. We also introduce derived metrics including lip-sync discrepancy and silent-audio-based lip-sync scores. In addition, we study how different identity reference selections affect leakage, providing insights into reference design. The proposed methodology is model-agnostic and establishes a more reliable benchmark for future research in talking face generation.

Dogucan Yaman, Seymanur Akti, Fevziye Irem Eyiokur et al.

We propose a text-to-talking-face synthesis framework leveraging latent speech representations from HierSpeech++. A Text-to-Vec module generates Wav2Vec2 embeddings from text, which jointly condition speech and face generation. To handle distribution shifts between clean and TTS-predicted features, we adopt a two-stage training: pretraining on Wav2Vec2 embeddings and finetuning on TTS outputs. This enables tight audio-visual alignment, preserves speaker identity, and produces natural, expressive speech and synchronized facial motion without ground-truth audio at inference. Experiments show that conditioning on TTS-predicted latent features outperforms cascaded pipelines, improving both lip-sync and visual realism.

Dogucan Yaman, Fevziye Irem Eyiokur, Leonard Bärmann et al.

In the task of talking face generation, the objective is to generate a face video with lips synchronized to the corresponding audio while preserving visual details and identity information. Current methods face the challenge of learning accurate lip synchronization while avoiding detrimental effects on visual quality, as well as robustly evaluating such synchronization. To tackle these problems, we propose utilizing an audio-visual speech representation expert (AV-HuBERT) for calculating lip synchronization loss during training. Moreover, leveraging AV-HuBERT's features, we introduce three novel lip synchronization evaluation metrics, aiming to provide a comprehensive assessment of lip synchronization performance. Experimental results, along with a detailed ablation study, demonstrate the effectiveness of our approach and the utility of the proposed evaluation metrics.

Fevziye Irem Eyiokur, Dogucan Yaman, Hazım Kemal Ekenel et al.

Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues. While prior works have shown progress in open-vocabulary object detection, they often fail in ambiguous scenarios where multiple candidate objects exist in the scene. To address these challenges, we propose a novel ERU framework that jointly leverages LLM-based data augmentation, depth-map modality, and a depth-aware decision module. This design enables robust integration of linguistic and embodied cues, improving disambiguation in complex or cluttered environments. Experimental results on two datasets demonstrate that our approach significantly outperforms existing baselines, achieving more accurate and reliable referent detection.

Fevziye Irem Eyiokur, Dogucan Yaman, Hazım Kemal Ekenel et al.

We address the problem of Embodied Reference Understanding, which involves predicting the object that a person in the scene is referring to through both pointing gesture and language. Accurately identifying the referent requires multimodal understanding: integrating textual instructions, visual pointing, and scene context. However, existing methods often struggle to effectively leverage visual clues for disambiguation. We also observe that, while the referent is often aligned with the head-to-fingertip line, it occasionally aligns more closely with the wrist-to-fingertip line. Therefore, relying on a single line assumption can be overly simplistic and may lead to suboptimal performance. To address this, we propose a dual-model framework, where one model learns from the head-to-fingertip direction and the other from the wrist-to-fingertip direction. We further introduce a Gaussian ray heatmap representation of these lines and use them as input to provide a strong supervisory signal that encourages the model to better attend to pointing cues. To combine the strengths of both models, we present the CLIP-Aware Pointing Ensemble module, which performs a hybrid ensemble based on CLIP features. Additionally, we propose an object center prediction head as an auxiliary task to further enhance referent localization. We validate our approach through extensive experiments and analysis on the benchmark YouRefIt dataset, achieving an improvement of approximately 4 mAP at the 0.25 IoU threshold. We further evaluate our approach on the CAESAR and ISL Pointing datasets.

Dogucan Yaman, Fevziye Irem Eyiokur, Leonard Bärmann et al.

Audio-Driven Talking Face Generation aims at generating realistic videos of talking faces, focusing on accurate audio-lip synchronization without deteriorating any identity-related visual details. Recent state-of-the-art methods are based on inpainting, meaning that the lower half of the input face is masked, and the model fills the masked region by generating lips aligned with the given audio. Hence, to preserve identity-related visual details from the lower half, these approaches additionally require an unmasked identity reference image randomly selected from the same video. However, this common masking strategy suffers from (1) information loss in the input faces, significantly affecting the networks' ability to preserve visual quality and identity details, (2) variation between identity reference and input image degrading reconstruction performance, and (3) the identity reference negatively impacting the model, causing unintended copying of elements unaligned with the audio. To address these issues, we propose a mask-free talking face generation approach while maintaining the 2D-based face editing task. Instead of masking the lower half, we transform the input images to have closed mouths, using a two-step landmark-based approach trained in an unpaired manner. Subsequently, we provide these edited but unmasked faces to a lip adaptation model alongside the audio to generate appropriate lip movements. Thus, our approach needs neither masked input images nor identity reference images. We conduct experiments on the benchmark LRS2 and HDTF datasets and perform various ablation studies to validate our contributions.

Fevziye Irem Eyiokur, Christian Huber, Thai-Binh Nguyen et al.

In this paper, we report on communication experiments conducted in the summer of 2022 during a deep dive to the wreck of the Titanic. Radio transmission is not possible in deep sea water, and communication links rely on sonar signals. Due to the low bandwidth of sonar signals and the need to communicate readable data, text messaging is used in deep-sea missions. In this paper, we report results and experiences from a messaging system that converts speech to text in a submarine, sends text messages to the surface, and reconstructs those messages as synthetic lip-synchronous videos of the speakers. The resulting system was tested during an actual dive to Titanic in the summer of 2022. We achieved an acceptable latency for a system of such complexity as well as good quality. The system demonstration video can be found at the following link: https://youtu.be/C4lyM86-5Ig

Dogucan Yaman, Hazım Kemal Ekenel, Alexander Waibel

In the portrait matting, the goal is to predict an alpha matte that identifies the effect of each pixel on the foreground subject. Traditional approaches and most of the existing works utilized an additional input, e.g., trimap, background image, to predict alpha matte. However, (1) providing additional input is not always practical, and (2) models are too sensitive to these additional inputs. To address these points, in this paper, we introduce an additional input-free approach to perform portrait matting. We divide the task into two subtasks, segmentation and alpha matte prediction. We first generate a coarse segmentation map from the input image and then predict the alpha matte by utilizing the image and segmentation map. Besides, we present a segmentation encoding block to downsample the coarse segmentation map and provide useful feature representation to the residual block, since using a single encoder causes the vanishing of the segmentation information. We tested our model on four different benchmark datasets. The proposed method outperformed the MODNet and MGMatting methods that also take a single input. Besides, we obtained comparable results with BGM-V2 and FBA methods that require additional input.

Henning Schulze, Dogucan Yaman, Alexander Waibel

Generating images according to natural language descriptions is a challenging task. Prior research has mainly focused to enhance the quality of generation by investigating the use of spatial attention and/or textual attention thereby neglecting the relationship between channels. In this work, we propose the Combined Attention Generative Adversarial Network (CAGAN) to generate photo-realistic images according to textual descriptions. The proposed CAGAN utilises two attention models: word attention to draw different sub-regions conditioned on related words; and squeeze-and-excitation attention to capture non-linear interaction among channels. With spectral normalisation to stabilise training, our proposed CAGAN improves the state of the art on the IS and FID on the CUB dataset and the FID on the more challenging COCO dataset. Furthermore, we demonstrate that judging a model by a single evaluation metric can be misleading by developing an additional model adding local self-attention which scores a higher IS, outperforming the state of the art on the CUB dataset, but generates unrealistic images through feature repetition.

Dogucan Yaman, Fevziye Irem Eyiokur, Hazım Kemal Ekenel

In this paper, we explore the correlation between different visual biometric modalities. For this purpose, we present an end-to-end deep neural network model that learns a mapping between the biometric modalities. Namely, our goal is to generate a frontal face image of a subject given his/her ear image as the input. We formulated the problem as a paired image-to-image translation task and collected datasets of ear and face image pairs from the Multi-PIE and FERET datasets to train our GAN-based models. We employed feature reconstruction and style reconstruction losses in addition to adversarial and pixel losses. We evaluated the proposed method both in terms of reconstruction quality and in terms of person identification accuracy. To assess the generalization capability of the learned mapping models, we also run cross-dataset experiments. That is, we trained the model on the FERET dataset and tested it on the Multi-PIE dataset and vice versa. We have achieved very promising results, especially on the FERET dataset, generating visually appealing face images from ear image inputs. Moreover, we attained a very high cross-modality person identification performance, for example, reaching 90.9% Rank-10 identification accuracy on the FERET dataset.

Dogucan Yaman, Fevziye Irem Eyiokur, Hazım Kemal Ekenel

In this paper, we present multimodal deep neural network frameworks for age and gender classification, which take input a profile face image as well as an ear image. Our main objective is to enhance the accuracy of soft biometric trait extraction from profile face images by additionally utilizing a promising biometric modality: ear appearance. For this purpose, we provided end-to-end multimodal deep learning frameworks. We explored different multimodal strategies by employing data, feature, and score level fusion. To increase representation and discrimination capability of the deep neural networks, we benefited from domain adaptation and employed center loss besides softmax loss. We conducted extensive experiments on the UND-F, UND-J2, and FERET datasets. Experimental results indicated that profile face images contain a rich source of information for age and gender classification. We found that the presented multimodal system achieves very high age and gender classification accuracies. Moreover, we attained superior results compared to the state-of-the-art profile face image or ear image-based age and gender classification methods.

Žiga Emeršič, Aruna Kumar S. V., B. S. Harish et al.

This paper presents a summary of the 2019 Unconstrained Ear Recognition Challenge (UERC), the second in a series of group benchmarking efforts centered around the problem of person recognition from ear images captured in uncontrolled settings. The goal of the challenge is to assess the performance of existing ear recognition techniques on a challenging large-scale ear dataset and to analyze performance of the technology from various viewpoints, such as generalization abilities to unseen data characteristics, sensitivity to rotations, occlusions and image resolution and performance bias on sub-groups of subjects, selected based on demographic criteria, i.e. gender and ethnicity. Research groups from 12 institutions entered the competition and submitted a total of 13 recognition approaches ranging from descriptor-based methods to deep-learning models. The majority of submissions focused on ensemble based methods combining either representations from multiple deep models or hand-crafted with learned image descriptors. Our analysis shows that methods incorporating deep learning models clearly outperform techniques relying solely on hand-crafted descriptors, even though both groups of techniques exhibit similar behaviour when it comes to robustness to various covariates, such presence of occlusions, changes in (head) pose, or variability in image resolution. The results of the challenge also show that there has been considerable progress since the first UERC in 2017, but that there is still ample room for further research in this area.

Dogucan Yaman, Fevziye Irem Eyiokur, Nurdan Sezgin et al.

In this paper, we present a detailed analysis on extracting soft biometric traits, age and gender, from ear images. Although there have been a few previous work on gender classification using ear images, to the best of our knowledge, this study is the first work on age classification from ear images. In the study, we have utilized both geometric features and appearance-based features for ear representation. The utilized geometric features are based on eight anthropometric landmarks and consist of 14 distance measurements and two area calculations. The appearance-based methods employ deep convolutional neural networks for representation and classification. The well-known convolutional neural network models, namely, AlexNet, VGG-16, GoogLeNet, and SqueezeNet have been adopted for the study. They have been fine-tuned on a large-scale ear dataset that has been built from the profile and close-to-profile face images in the Multi-PIE face dataset. This way, we have performed a domain adaptation. The updated models have been fine-tuned once more time on the small-scale target ear dataset, which contains only around 270 ear images for training. According to the experimental results, appearance-based methods have been found to be superior to the methods based on geometric features. We have achieved 94\% accuracy for gender classification, whereas 52\% accuracy has been obtained for age classification. These results indicate that ear images provide useful cues for age and gender classification, however, further work is required for age estimation.

Fevziye Irem Eyiokur, Dogucan Yaman, Hazım Kemal Ekenel

In this paper, we have extensively investigated the unconstrained ear recognition problem. We have first shown the importance of domain adaptation, when deep convolutional neural network models are used for ear recognition. To enable domain adaptation, we have collected a new ear dataset using the Multi-PIE face dataset, which we named as Multi-PIE ear dataset. To improve the performance further, we have combined different deep convolutional neural network models. We have analyzed in depth the effect of ear image quality, for example illumination and aspect ratio, on the classification performance. Finally, we have addressed the problem of dataset bias in the ear recognition field. Experiments on the UERC dataset have shown that domain adaptation leads to a significant performance improvement. For example, when VGG-16 model is used and the domain adaptation is applied, an absolute increase of around 10\% has been achieved. Combining different deep convolutional neural network models has further improved the accuracy by 4\%. It has also been observed that image quality has an influence on the results. In the experiments that we have conducted to examine the dataset bias, given an ear image, we were able to classify the dataset that it has come from with 99.71\% accuracy, which indicates a strong bias among the ear recognition datasets.

Žiga Emeršič, Dejan Štepec, Vitomir Štruc et al.

In this paper we present the results of the Unconstrained Ear Recognition Challenge (UERC), a group benchmarking effort centered around the problem of person recognition from ear images captured in uncontrolled conditions. The goal of the challenge was to assess the performance of existing ear recognition techniques on a challenging large-scale dataset and identify open problems that need to be addressed in the future. Five groups from three continents participated in the challenge and contributed six ear recognition techniques for the evaluation, while multiple baselines were made available for the challenge by the UERC organizers. A comprehensive analysis was conducted with all participating approaches addressing essential research questions pertaining to the sensitivity of the technology to head rotation, flipping, gallery size, large-scale recognition and others. The top performer of the UERC was found to ensure robust performance on a smaller part of the dataset (with 180 subjects) regardless of image characteristics, but still exhibited a significant performance drop when the entire dataset comprising 3,704 subjects was used for testing.