Xuhua Ren

Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng et al.

Human image animation has witnessed significant advancements, yet generating high-fidelity hand motions remains a persistent challenge due to their high degrees of freedom and motion complexity. While reinforcement learning from human feedback, particularly direct preference optimization, offers a potential solution, it necessitates the construction of strict preference pairs. However, curating such pairs for dynamic hand regions is prohibitively expensive and often impractical due to frame-wise inconsistencies. In this paper, we propose Implicit Preference Alignment (IPA), a data-efficient post-training framework that eliminates the need for paired preference data. Theoretically grounded in implicit reward maximization, IPA aligns the model by maximizing the likelihood of self-generated high-quality samples while penalizing deviations from the pretrained prior. Furthermore, we introduce a Hand-Aware Local Optimization mechanism to explicitly steer the alignment process toward hand regions. Experiments demonstrate that our method achieves effective preference optimization to enhance hand generation quality, while significantly lowering the barrier for constructing preference data. Codes are released at https://github.com/mdswyz/IPA

Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng et al.

Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose \textit{FaithfulFaces}, a pose-faithful facial identity preservation learning framework to improve IPT2V in complex dynamic scenes. The key of FaithfulFaces is a pose-shared identity aligner that refines and aligns facial poses across distinct views via a pose-shared dictionary and a pose variation-identity invariance constraint. By mapping single-view inputs into a global facial pose representation with explicit Euler angle embeddings, FaithfulFaces provides a pose-faithful facial prior that guides generative foundations toward robust identity-preserving generation. In particular, we develop a specialized pipeline to curate a high-quality video dataset featuring substantial facial pose diversity. Extensive experiments demonstrate that FaithfulFaces achieves state-of-the-art performance, maintaining superior identity consistency and structural clarity even as pose changes and occlusions occur.

Jiaxiang Cheng, Bing Ma, Xuhua Ren et al.

Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapted from image-based techniques, lack a single-step distillation ability for large-scale video models and task generalization for conditional downstream tasks. To bridge this gap, we propose the Video Phased Adversarial Equilibrium (V-PAE), a distillation framework that enables high-quality, single-step video generation from large-scale video models. Our approach employs a two-phase process. (i) Stability priming is a warm-up process to align the distributions of real and generated videos. It improves the stability of single-step adversarial distillation in the following process. (ii) Unified adversarial equilibrium is a flexible self-adversarial process that reuses generator parameters for the discriminator backbone. It achieves a co-evolutionary adversarial equilibrium in the Gaussian noise space. For the conditional tasks, we primarily preserve video-image subject consistency, which is caused by semantic degradation and conditional frame collapse during the distillation training in image-to-video (I2V) generation. Comprehensive experiments on VBench-I2V demonstrate that V-PAE outperforms existing acceleration methods by an average of 5.8% in the overall quality score, including semantic alignment, temporal coherence, and frame quality. In addition, our approach reduces the diffusion latency of the large-scale video model (e.g., Wan2.1-I2V-14B) by 100 times, while preserving competitive performance.

Ruihuang Li, Caijin Zhou, Shoujian Zheng et al. · tencent-ai

Intelligent game creation represents a transformative advancement in game development, utilizing generative artificial intelligence to dynamically generate and enhance game content. Despite notable progress in generative models, the comprehensive synthesis of high-quality game assets, including both images and videos, remains a challenging frontier. To create high-fidelity game content that simultaneously aligns with player preferences and significantly boosts designer efficiency, we present Hunyuan-Game, an innovative project designed to revolutionize intelligent game production. Hunyuan-Game encompasses two primary branches: image generation and video generation. The image generation component is built upon a vast dataset comprising billions of game images, leading to the development of a group of customized image generation models tailored for game scenarios: (1) General Text-to-Image Generation. (2) Game Visual Effects Generation, involving text-to-effect and reference image-based game visual effect generation. (3) Transparent Image Generation for characters, scenes, and game visual effects. (4) Game Character Generation based on sketches, black-and-white images, and white models. The video generation component is built upon a comprehensive dataset of millions of game and anime videos, leading to the development of five core algorithmic models, each targeting critical pain points in game development and having robust adaptation to diverse game video scenarios: (1) Image-to-Video Generation. (2) 360 A/T Pose Avatar Video Synthesis. (3) Dynamic Illustration Generation. (4) Generative Video Super-Resolution. (5) Interactive Game Video Generation. These image and video generation models not only exhibit high-level aesthetic expression but also deeply integrate domain-specific knowledge, establishing a systematic understanding of diverse game and anime art styles.

Ruojun Xu, Yu Kai, Xuhua Ren et al.

Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. However, a critical limitation of DPO is likelihood displacement, where the probabilities of chosen samples paradoxically decrease during training, undermining the quality of generation. Although this issue has been investigated in autoregressive models, its impact within diffusion-based models remains largely unexplored. This gap leads to suboptimal performance in tasks involving video generation. To address this, we conduct a formal analysis of DPO loss through updating policy within the diffusion framework, which describes how the updating of specific training samples influences the model's predictions on other samples. Using this tool, we identify two main failure modes: (1) Optimization Conflict, which arises from small reward margins between chosen and rejected samples, and (2) Suboptimal Maximization, caused by large reward margins. Informed by these insights, we introduce a novel solution named Policy-Guided DPO (PG-DPO), combining Adaptive Rejection Scaling (ARS) and Implicit Preference Regularization (IPR) to effectively mitigate likelihood displacement. Experiments show that PG-DPO outperforms existing methods in both quantitative metrics and qualitative evaluations, offering a robust solution for improving preference alignment in video generation tasks.

Xiaolu Hou, Bing Ma, Jiaxiang Cheng et al.

With the growing demand for short videos and personalized content, automated Video Log (Vlog) generation has become a key direction in multimodal content creation. Existing methods mostly rely on predefined scripts, lacking dynamism and personal expression. Therefore, there is an urgent need for an automated Vlog generation approach that enables effective multimodal collaboration and high personalization. To this end, we propose PersonaVlog, an automated multimodal stylized Vlog generation framework that can produce personalized Vlogs featuring videos, background music, and inner monologue speech based on a given theme and reference image. Specifically, we propose a multi-agent collaboration framework based on Multimodal Large Language Models (MLLMs). This framework efficiently generates high-quality prompts for multimodal content creation based on user input, thereby improving the efficiency and creativity of the process. In addition, we incorporate a feedback and rollback mechanism that leverages MLLMs to evaluate and provide feedback on generated results, thereby enabling iterative self-correction of multimodal content. We also propose ThemeVlogEval, a theme-based automated benchmarking framework that provides standardized metrics and datasets for fair evaluation. Comprehensive experiments demonstrate the significant advantages and potential of our framework over several baselines, highlighting its effectiveness and great potential for generating automated Vlogs.

Xuhua Ren, Hengcan Shi, Jin Li

Scene text recognition is an important and challenging task in computer vision. However, most prior works focus on recognizing pre-defined words, while there are various out-of-vocabulary (OOV) words in real-world applications. In this paper, we propose a novel open-vocabulary text recognition framework, Pseudo-OCR, to recognize OOV words. The key challenge in this task is the lack of OOV training data. To solve this problem, we first propose a pseudo label generation module that leverages character detection and image inpainting to produce substantial pseudo OOV training data from real-world images. Unlike previous synthetic data, our pseudo OOV data contains real characters and backgrounds to simulate real-world applications. Secondly, to reduce noises in pseudo data, we present a semantic checking mechanism to filter semantically meaningful data. Thirdly, we introduce a quality-aware margin loss to boost the training with pseudo data. Our loss includes a margin-based part to enhance the classification ability, and a quality-aware part to penalize low-quality samples in both real and pseudo data. Extensive experiments demonstrate that our approach outperforms the state-of-the-art on eight datasets and achieves the first rank in the ICDAR2022 challenge.

Sheng Wang, Jiayu Huo, Xi Ouyang et al.

Computer-aided diagnosis with deep learning techniques has been shown to be helpful for the diagnosis of the mammography in many clinical studies. However, the image styles of different vendors are very distinctive, and there may exist domain gap among different vendors that could potentially compromise the universal applicability of one deep learning model. In this study, we explicitly address style variety issue with the proposed multi-resolution and multi-reference neural style transfer (mr2NST) network. The mr2NST can normalize the styles from different vendors to the same style baseline with very high resolution. We illustrate that the image quality of the transferred images is comparable to the quality of original images of the target domain (vendor) in terms of NIMA scores. Meanwhile, the mr2NST results are also shown to be helpful for the lesion detection in mammograms.

Xuhua Ren, Jiayu Huo, Kai Xuan et al.

Brain magnetic resonance (MR) segmentation for hydrocephalus patients is considered as a challenging work. Encoding the variation of the brain anatomical structures from different individuals cannot be easily achieved. The task becomes even more difficult especially when the image data from hydrocephalus patients are considered, which often have large deformations and differ significantly from the normal subjects. Here, we propose a novel strategy with hard and soft attention modules to solve the segmentation problems for hydrocephalus MR images. Our main contributions are three-fold: 1) the hard-attention module generates coarse segmentation map using multi-atlas-based method and the VoxelMorph tool, which guides subsequent segmentation process and improves its robustness; 2) the soft-attention module incorporates position attention to capture precise context information, which further improves the segmentation accuracy; 3) we validate our method by segmenting insula, thalamus and many other regions-of-interests (ROIs) that are critical to quantify brain MR images of hydrocephalus patients in real clinical scenario. The proposed method achieves much improved robustness and accuracy when segmenting all 17 consciousness-related ROIs with high variations for different subjects. To the best of our knowledge, this is the first work to employ deep learning for solving the brain segmentation problems of hydrocephalus patients.

Xuhua Ren, Lichi Zhang, Qian Wang et al.

Medical image segmentation is challenging especially in dealing with small dataset of 3D MR images. Encoding the variation of brain anatomical struc-tures from individual subjects cannot be easily achieved, which is further chal-lenged by only a limited number of well labeled subjects for training. In this study, we aim to address the issue of brain MR image segmentation in small da-taset. First, concerning the limited number of training images, we adopt adver-sarial defense to augment the training data and therefore increase the robustness of the network. Second, inspired by the prior knowledge of neural anatomies, we reorganize the segmentation tasks of different regions into several groups in a hierarchical way. Third, the task reorganization extends to the semantic level, as we incorporate an additional object-level classification task to contribute high-order visual features toward the pixel-level segmentation task. In experiments we validate our method by segmenting gray matter, white matter, and several major regions on a challenge dataset. The proposed method with only seven subjects for training can achieve 84.46% of Dice score in the onsite test set.

Xuhua Ren, Lichi Zhang, Sahar Ahmad et al.

Semantic segmentation is essentially important to biomedical image analysis. Many recent works mainly focus on integrating the Fully Convolutional Network (FCN) architecture with sophisticated convolution implementation and deep supervision. In this paper, we propose to decompose the single segmentation task into three subsequent sub-tasks, including (1) pixel-wise image segmentation, (2) prediction of the class labels of the objects within the image, and (3) classification of the scene the image belonging to. While these three sub-tasks are trained to optimize their individual loss functions of different perceptual levels, we propose to let them interact by the task-task context ensemble. Moreover, we propose a novel sync-regularization to penalize the deviation between the outputs of the pixel-wise segmentation and the class prediction tasks. These effective regularizations help FCN utilize context information comprehensively and attain accurate semantic segmentation, even though the number of the images for training may be limited in many biomedical applications. We have successfully applied our framework to three diverse 2D/3D medical image datasets, including Robotic Scene Segmentation Challenge 18 (ROBOT18), Brain Tumor Segmentation Challenge 18 (BRATS18), and Retinal Fundus Glaucoma Challenge (REFUGE18). We have achieved top-tier performance in all three challenges.

Spyridon Bakas, Mauricio Reyes, Andras Jakab et al.

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.