Multimodal Language Learning Models (MLLMs) have shown remarkable performance in image understanding, generation, and editing, with recent advancements achieving pixel-level grounding with reasoning. However, these models for common objects struggle with fine-grained face understanding. In this work, we introduce the FacePlayGround-240K dataset, the first pioneering large-scale, pixel-grounded face caption and question-answer (QA) dataset that includes 240K images, 47 mask categories, 5.4M mask annotations, and 7.3M grounded regions, meticulously curated for alignment pretraining and instruction-tuning. We present the GroundingFace framework, specifically designed to enhance fine-grained face understanding. This framework significantly augments the capabilities of existing grounding models in face part segmentation, face attribute comprehension, while preserving general scene understanding. Comprehensive experiments validate that our approach surpasses current state-of-the-art models in pixel-grounded face captioning/QA and various downstream tasks, including face captioning, referring segmentation, and zero-shot face attribute recognition.

The study of talking face generation mainly explores the intricacies of synchronizing facial movements and crafting visually appealing, temporally-coherent animations. However, due to the limited exploration of global audio perception, current approaches predominantly employ auxiliary visual and spatial knowledge to stabilize the movements, which often results in the deterioration of the naturalness and temporal inconsistencies. Considering the essence of audio-driven animation, the audio signal serves as the ideal and unique priors to adjust facial expressions and lip movements, without resorting to interference of any visual signals. Based on this motivation, we propose a novel paradigm, dubbed as Sonic, to shift focus on the exploration of global audio perception. To effectively leverage global audio knowledge, we disentangle it into intra-and inter-clip audio perception and collaborate with both aspects to enhance overall perception. For the intra-clip audio perception, 1). Context-enhanced audio learning, in which long-range intra-clip temporal audio knowledge is extracted to provide facial expression and lip motion priors implicitly expressed as the tone and speed of speech. 2). Motion-decoupled controller, in which the motion of the head and expression movement are disentangled and independently controlled by intra-audio clips. Most importantly, for inter-clip audio perception, as a bridge to connect the intra-clips to achieve the global perception, Time-aware position shift fusion, in which the global inter-clip audio information is considered and fused for long-audio inference via through consecutively time-aware shifted windows. Extensive experiments demonstrate that the novel audio-driven paradigm outperform existing SOTA methodologies in terms of video quality, temporally consistency, lip synchronization precision, and motion diversity.

We introduce HunyuanPortrait, a diffusion-based condition control method that employs implicit representations for highly controllable and lifelike portrait animation. Given a single portrait image as an appearance reference and video clips as driving templates, HunyuanPortrait can animate the character in the reference image by the facial expression and head pose of the driving videos. In our framework, we utilize pre-trained encoders to achieve the decoupling of portrait motion information and identity in videos. To do so, implicit representation is adopted to encode motion information and is employed as control signals in the animation phase. By leveraging the power of stable video diffusion as the main building block, we carefully design adapter layers to inject control signals into the denoising unet through attention mechanisms. These bring spatial richness of details and temporal consistency. HunyuanPortrait also exhibits strong generalization performance, which can effectively disentangle appearance and motion under different image styles. Our framework outperforms existing methods, demonstrating superior temporal consistency and controllability. Our project is available at HunyuanPortrait.

Recent advances in Talking Head Generation (THG) have achieved impressive lip synchronization and visual quality through diffusion models; yet existing methods struggle to generate emotionally expressive portraits while preserving speaker identity. We identify three critical limitations in current emotional talking head generation: insufficient utilization of audio's inherent emotional cues, identity leakage in emotion representations, and isolated learning of emotion correlations. To address these challenges, we propose a novel framework dubbed as DICE-Talk, following the idea of disentangling identity with emotion, and then cooperating emotions with similar characteristics. First, we develop a disentangled emotion embedder that jointly models audio-visual emotional cues through cross-modal attention, representing emotions as identity-agnostic Gaussian distributions. Second, we introduce a correlation-enhanced emotion conditioning module with learnable emotion banks that explicitly capture inter-emotion relationships through vector quantization and attention-based feature aggregation. Third, we design an emotion discrimination objective that enforces affective consistency during the diffusion process through latent-space classification. Extensive experiments on MEAD and HDTF datasets demonstrate our method's superiority, outperforming state-of-the-art approaches in emotion accuracy while maintaining competitive lip-sync performance. Qualitative results and user studies further confirm our method's ability to generate identity-preserving portraits with rich, correlated emotional expressions that naturally adapt to unseen identities.

Blind face restoration, which aims to reconstruct high-quality images from low-quality inputs, can benefit many applications. Although existing generative-based methods achieve significant progress in producing high-quality images, they often fail to restore natural face shapes and high-fidelity facial details from severely-degraded inputs. In this work, we propose to integrate shape and generative priors to guide the challenging blind face restoration. Firstly, we set up a shape restoration module to recover reason-able facial geometry with 3D reconstruction. Secondly, a pretrained facial generator is adopted as decoder to generate photo-realistic high-resolution images. To ensure high-fidelity, hierarchical spatial features extracted from the low-quality inputs and rendered 3D images are inserted into the decoder with our proposed Adaptive Feature Fusion Block (AFFB). Moreover, we introduce hybrid-level losses to Jointly train the shape and generative priors together with other network parts such that these two priors better adapt to our blind face restoration task. The proposed Shape and Generative Prior integrated Network (SGPN) can re-store high-quality images with clear face shapes and real-istic facial details. Experimental results on synthetic and real-world datasets demonstrate SGPN performs favorably against state-of-the-art blind face restoration methods.

Injecting human knowledge is an effective way to accelerate reinforcement learning (RL). However, these methods are underexplored. This article presents our discovery that an abstract forward model [thought-game (TG)] combined with transfer learning is an effective way. We takeStarCraft IIas our study environment. With the help of a designed TG, the agent can learn a 99% win-rate on a 64×64 map against the Level-7 built-in AI, using only 1.08 h in a single commercial machine. We also show that the TG method is not as restrictive as it was thought to be. It can work with roughly designed TGs, and can also be useful when the environment changes. Comparing with previous model-based RL, we show TG is more effective. We also present a TG hypothesis that gives the influence of different fidelity levels of TG. For real games that have unequal state and action spaces, we proposed a novel XfrNet of which usefulness is validated while achieving a 90% win-rate against the cheating Level-10 AI. We argue that the TG method might shed light on further studies of efficient RL with human knowledge.

Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always fail in real-world scene, since the Low-Resolution (LR) images after the ideal degradation (e.g., bicubic down-sampling) deviate from real source domain. The domain gap between the LR images and the real-world images can be observed clearly on frequency density, which inspires us to explicitly narrow the undesired gap caused by incorrect degradation. From this point of view, we design a novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying existing SR methods to the real scene. We estimate degradation kernels from unsupervised images and generate the corresponding LR images. To provide useful gradient information for kernel estimation, we propose Frequency Density Comparator (FDC) by distinguishing the frequency density of images on different scales. Based on the domain-consistent LR-HR pairs, we train easy-implemented Convolutional Neural Network (CNN) SR models. Extensive experiments show that the proposed FCA improves the performance of the SR model under real-world setting achieving state-of-the-art results with high fidelity and plausible perception, thus providing a novel effective framework for real-world SR application.

Deep-learning based Super-Resolution (SR) methods have exhibited promising performance under non-blind setting where blur kernel is known; however, blur kernels of Low-Resolution (LR) images in different practical applications are usually unknown. It may lead to a significant performance drop when degradation process of training images deviates from that of real images. In this paper, we propose a novel blind SR framework to super-resolve LR images degraded by arbitrary blur kernel with accurate kernel estimation in frequency domain. To our best knowledge, this is the first deep learning method which conducts blur kernel estimation in frequency domain. Specifically, we first demonstrate that feature representation in frequency domain is more conducive for blur kernel reconstruction than in spatial domain. Next, we present a Spectrum-to-Kernel (S$2$K) network to estimate general blur kernels in diverse forms. We use a conditional GAN (CGAN) combined with SR-oriented optimization target to learn the end-to-end translation from degraded images' spectra to unknown kernels. Extensive experiments on both synthetic and real-world images demonstrate that our proposed method sufficiently reduces blur kernel estimation error, thus enables the off-the-shelf non-blind SR methods to work under blind setting effectively, and achieves superior performance over state-of-the-art blind SR methods, averagely by 1.39dB, 0.48dB (Gaussian kernels) and 6.15dB, 4.57dB (motion kernels) for scales $2\times$ and $4\times$ respectively.

This paper proposes a novel two-factor attention based encoder-decoder model (TwoFactorEncoderDecoder) for multivariate weather prediction. The proposed model learns attention weights from two factors, namely, temporal information and prior knowledge inferred information. Here, temporal information contains change patterns hidden in observed time series data, while prior knowledge inferred information gives various types of meteorological observations in weather forecasting. Attention weights of the two factors are used to select the intermediate outputs of the encoder, and then combine the selected result with information inferred by prior knowledge for weather forecasting by a more effective way. In addition, this paper proposes a loss function for multivariate prediction. Compared with Mean Square Error (MSE) loss function, the proposed loss function can fit small variances more accurately in performing multivariate prediction. Compared with the attention model that only uses temporal information or the prior knowledge inferred information, the proposed TwoFactorEncoderDecoder model has encouraging improvements in prediction accuracy on the public weather forecasting dataset, namely, the MAPE of t2m is increased by 5.42%, the MAPE of rh2m is increased by 2.92%, and the MAPE of w2m is increased by 1.67%, which shows the effect of the two-factor attention mechanism. Source code for the complete system will be available at https://github.com/YuanMLer/TFAEncoderDecoder.