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

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.

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.