Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation

Gaze estimation methods encounter significant performance deterioration when being evaluated across different domains, because of the domain gap between the testing and training data. Existing methods try to solve this issue by reducing the deviation of data distribution, however, they ignore the existence of label deviation in the data due to the acquisition mechanism of the gaze label and the individual physiological differences. In this paper, we first point out that the influence brought by the label deviation cannot be ignored, and propose a gaze label alignment algorithm (GLA) to eliminate the label distribution deviation. Specifically, we first train the feature extractor on all domains to get domain invariant features, and then select an anchor domain to train the gaze regressor. We predict the gaze label on remaining domains and use a mapping function to align the labels. Finally, these aligned labels can be used to train gaze estimation models. Therefore, our method can be combined with any existing method. Experimental results show that our GLA method can effectively alleviate the label distribution shift, and SOTA gaze estimation methods can be further improved obviously.

Suppressing Uncertainty in Gaze Estimation

Uncertainty in gaze estimation manifests in two aspects: 1) low-quality images caused by occlusion, blurriness, inconsistent eye movements, or even non-face images; 2) incorrect labels resulting from the misalignment between the labeled and actual gaze points during the annotation process. Allowing these uncertainties to participate in training hinders the improvement of gaze estimation. To tackle these challenges, in this paper, we propose an effective solution, named Suppressing Uncertainty in Gaze Estimation (SUGE), which introduces a novel triplet-label consistency measurement to estimate and reduce the uncertainties. Specifically, for each training sample, we propose to estimate a novel ``neighboring label'' calculated by a linearly weighted projection from the neighbors to capture the similarity relationship between image features and their corresponding labels, which can be incorporated with the predicted pseudo label and ground-truth label for uncertainty estimation. By modeling such triplet-label consistency, we can measure the qualities of both images and labels, and further largely reduce the negative effects of unqualified images and wrong labels through our designed sample weighting and label correction strategies. Experimental results on the gaze estimation benchmarks indicate that our proposed SUGE achieves state-of-the-art performance.

EM-Net: Gaze Estimation with Expectation Maximization Algorithm

In recent years, the accuracy of gaze estimation techniques has gradually improved, but existing methods often rely on large datasets or large models to improve performance, which leads to high demands on computational resources. In terms of this issue, this paper proposes a lightweight gaze estimation model EM-Net based on deep learning and traditional machine learning algorithms Expectation Maximization algorithm. First, the proposed Global Attention Mechanism(GAM) is added to extract features related to gaze estimation to improve the model's ability to capture global dependencies and thus improve its performance. Second, by learning hierarchical feature representations through the EM module, the model has strong generalization ability, which reduces the need for sample size. Experiments have confirmed that, on the premise of using only 50% of the training data, EM-Net improves the performance of Gaze360, MPIIFaceGaze, and RT-Gene datasets by 2.2%, 2.02%, and 2.03%, respectively, compared with GazeNAS-ETH. It also shows good robustness in the face of Gaussian noise interference.

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders

We address the problem of gaze target estimation, which aims to predict where a person is looking in a scene. Predicting a person's gaze target requires reasoning both about the person's appearance and the contents of the scene. Prior works have developed increasingly complex, hand-crafted pipelines for gaze target estimation that carefully fuse features from separate scene encoders, head encoders, and auxiliary models for signals like depth and pose. Motivated by the success of general-purpose feature extractors on a variety of visual tasks, we propose Gaze-LLE, a novel transformer framework that streamlines gaze target estimation by leveraging features from a frozen DINOv2 encoder. We extract a single feature representation for the scene, and apply a person-specific positional prompt to decode gaze with a lightweight module. We demonstrate state-of-the-art performance across several gaze benchmarks and provide extensive analysis to validate our design choices. Our code is available at: http://github.com/fkryan/gazelle .

GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expression

Audio-driven talking head generation necessitates seamless integration of audio and visual data amidst the challenges posed by diverse input portraits and intricate correlations between audio and facial motions. In response, we propose a robust framework GoHD designed to produce highly realistic, expressive, and controllable portrait videos from any reference identity with any motion. GoHD innovates with three key modules: Firstly, an animation module utilizing latent navigation is introduced to improve the generalization ability across unseen input styles. This module achieves high disentanglement of motion and identity, and it also incorporates gaze orientation to rectify unnatural eye movements that were previously overlooked. Secondly, a conformer-structured conditional diffusion model is designed to guarantee head poses that are aware of prosody. Thirdly, to estimate lip-synchronized and realistic expressions from the input audio within limited training data, a two-stage training strategy is devised to decouple frequent and frame-wise lip motion distillation from the generation of other more temporally dependent but less audio-related motions, e.g., blinks and frowns. Extensive experiments validate GoHD's advanced generalization capabilities, demonstrating its effectiveness in generating realistic talking face results on arbitrary subjects.

Lightweight Gaze Estimation Model Via Fusion Global Information

Deep learning-based appearance gaze estimation methods are gaining popularity due to their high accuracy and fewer constraints from the environment. However, existing high-precision models often rely on deeper networks, leading to problems such as large parameters, long training time, and slow convergence. In terms of this issue, this paper proposes a novel lightweight gaze estimation model FGI-Net(Fusion Global Information). The model fuses global information into the CNN, effectively compensating for the need of multi-layer convolution and pooling to indirectly capture global information, while reducing the complexity of the model, improving the model accuracy and convergence speed. To validate the performance of the model, a large number of experiments are conducted, comparing accuracy with existing classical models and lightweight models, comparing convergence speed with models of different architectures, and conducting ablation experiments. Experimental results show that compared with GazeCaps, the latest gaze estimation model, FGI-Net achieves a smaller angle error with 87.1% and 79.1% reduction in parameters and FLOPs, respectively (MPIIFaceGaze is 3.74{\deg}, EyeDiap is 5.15{\deg}, Gaze360 is 10.50{\deg} and RT-Gene is 6.02{\deg}). Moreover, compared with different architectural models such as CNN and Transformer, FGI-Net is able to quickly converge to a higher accuracy range with fewer iterations of training, when achieving optimal accuracy on the Gaze360 and EyeDiap datasets, the FGI-Net model has 25% and 37.5% fewer iterations of training compared to GazeTR, respectively.

Multi-task Gaze Estimation Via Unidirectional Convolution

Using lightweight models as backbone networks in gaze estimation tasks often results in significant performance degradation. The main reason is that the number of feature channels in lightweight networks is usually small, which makes the model expression ability limited. In order to improve the performance of lightweight models in gaze estimation tasks, a network model named Multitask-Gaze is proposed. The main components of Multitask-Gaze include Unidirectional Convolution (UC), Spatial and Channel Attention (SCA), Global Convolution Module (GCM), and Multi-task Regression Module(MRM). UC not only significantly reduces the number of parameters and FLOPs, but also extends the receptive field and improves the long-distance modeling capability of the model, thereby improving the model performance. SCA highlights gaze-related features and suppresses gaze-irrelevant features. The GCM replaces the pooling layer and avoids the performance degradation due to information loss. MRM improves the accuracy of individual tasks and strengthens the connections between tasks for overall performance improvement. The experimental results show that compared with the State-of-the-art method SUGE, the performance of Multitask-Gaze on MPIIFaceGaze and Gaze360 datasets is improved by 1.71% and 2.75%, respectively, while the number of parameters and FLOPs are significantly reduced by 75.5% and 86.88%.

Towards Pixel-Level Prediction for Gaze Following: Benchmark and Approach

Following the gaze of other people and analyzing the target they are looking at can help us understand what they are thinking, and doing, and predict the actions that may follow. Existing methods for gaze following struggle to perform well in natural scenes with diverse objects, and focus on gaze points rather than objects, making it difficult to deliver clear semantics and accurate scope of the targets. To address this shortcoming, we propose a novel gaze target prediction solution named GazeSeg, that can fully utilize the spatial visual field of the person as guiding information and lead to a progressively coarse-to-fine gaze target segmentation and recognition process. Specifically, a prompt-based visual foundation model serves as the encoder, working in conjunction with three distinct decoding modules (e.g. FoV perception, heatmap generation, and segmentation) to form the framework for gaze target prediction. Then, with the head bounding box performed as an initial prompt, GazeSeg obtains the FoV map, heatmap, and segmentation map progressively, leading to a unified framework for multiple tasks (e.g. direction estimation, gaze target segmentation, and recognition). In particular, to facilitate this research, we construct and release a new dataset, comprising 72k images with pixel-level annotations and 270 categories of gaze targets, built upon the GazeFollow dataset. The quantitative evaluation shows that our approach achieves the Dice of 0.325 in gaze target segmentation and 71.7% top-5 recognition. Meanwhile, our approach also outperforms previous state-of-the-art methods, achieving 0.953 in AUC on the gaze-following task. The dataset and code will be released.

GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splatting

Gaze estimation encounters generalization challenges when dealing with out-of-distribution data. To address this problem, recent methods use neural radiance fields (NeRF) to generate augmented data. However, existing methods based on NeRF are computationally expensive and lack facial details. 3D Gaussian Splatting (3DGS) has become the prevailing representation of neural fields. While 3DGS has been extensively examined in head avatars, it faces challenges with accurate gaze control and generalization across different subjects. In this work, we propose GazeGaussian, a high-fidelity gaze redirection method that uses a two-stream 3DGS model to represent the face and eye regions separately. By leveraging the unstructured nature of 3DGS, we develop a novel eye representation for rigid eye rotation based on the target gaze direction. To enhance synthesis generalization across various subjects, we integrate an expression-conditional module to guide the neural renderer. Comprehensive experiments show that GazeGaussian outperforms existing methods in rendering speed, gaze redirection accuracy, and facial synthesis across multiple datasets. We also demonstrate that existing gaze estimation methods can leverage GazeGaussian to improve their generalization performance. The code will be available at: https://ucwxb.github.io/GazeGaussian/.

LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimation

The ability of gaze estimation models to generalize is often significantly hindered by various factors unrelated to gaze, especially when the training dataset is limited. Current strategies aim to address this challenge through different domain generalization techniques, yet they have had limited success due to the risk of overfitting when solely relying on value labels for regression. Recent progress in pre-trained vision-language models has motivated us to capitalize on the abundant semantic information available. We propose a novel approach in this paper, reframing the gaze estimation task as a vision-language alignment issue. Our proposed framework, named Language-Guided Gaze Estimation (LG-Gaze), learns continuous and geometry-sensitive features for gaze estimation benefit from the rich prior knowledges of vision-language models. Specifically, LG-Gaze aligns gaze features with continuous linguistic features through our proposed multimodal contrastive regression loss, which customizes adaptive weights for different negative samples. Furthermore, to better adapt to the labels for gaze estimation task, we propose a geometry-aware interpolation method to obtain more precise gaze embeddings. Through extensive experiments, we validate the efficacy of our framework in four different cross-domain evaluation tasks.