The prestigious academic conference in the field of artificial intelligence, IJCAI (International Joint Conference on Artificial Intelligence) 2024, has officially kicked off. This year, the latest research paper from OPPO AI Center was officially selected for the IJCAI 2024 event. OPPO also made a remarkable appearance with multiple cutting-edge AI innovations and features, actively positioning itself at the forefront of continuous innovation in AI phones.
Innovative Zero-Shot Framework Revolutionizes Text-to-Image Video Generation
At the IJCAI 2024 conference, OPPO AI Center’s latest research paper, “Zero-shot High-fidelity and Pose-controllable Character Animation,” was highlighted, once again demonstrating OPPO’s extensive technological expertise and continuous progress in the field of AI. Currently, in the I2V (Image-to-Video) field, the most common problems are inconsistent character appearances and poor detail retention, requiring large amounts of video data for training and consuming significant computing resources. To address these challenges, OPPO AI Center introduced PoseAnimate, an innovative zero-shot I2V framework. PoseAnimate leverages pose information to control animation movements while maintaining the consistency of scene content. This framework achieves its goals through three key modules: Pose-Aware Control Module (PACM): Integrates various pose signals into text embeddings to retain character-irrelevant content and ensure accurate motion alignment. Dual-Consistency Attention Module (DCAM): Improves temporal consistency, preserving character identity and intricate background details. Mask-Guided Decoupling Module (MGDM): Improves the fidelity of generated videos by decoupling characters from the background. The OPPO team also proposed the Pose Alignment Transition Algorithm (PATA) to ensure smooth character pose alignment and transitions. Experimental results demonstrate that PoseAnimate significantly outperforms existing state-of-the-art training methods in character consistency and detail fidelity, maintaining high temporal consistency throughout the generated animations. In addition, Dr. Yang Zhenyu from OPPO AI Center was invited to give a presentation at the IJCAI 2024 conference on “Generative AI for Smartphone: Challenges, Opportunities, and Practices of OPPO”. He shared OPPO’s practical experiences with AI industry partners and academia, contributing to the global exploration of how the next generation of smartphones can responsibly and effectively integrate AI technology.
Accelerating the application of generative AI technology, ushering in a new era of AI phones With the rapid development of generative AI technology, the smartphone industry is entering a new era of AI phones. As a global leader, OPPO is committed to integrating cutting-edge AI technology into its products, bringing a smarter and more convenient mobile life experience to users. This year, OPPO launched the Find X7 Series and Reno12 Series 5G AI phones, showcasing OPPO’s profound prowess in mobile AI. At the same time, OPPO is accelerating the global democratization of AI phones, aiming to bring generative AI features to its entire smartphone lineup for approximately 50 million users within a year. OPPO firmly believes that a true AI smartphone is not just about hardware improvement, but also a revolutionary breakthrough in user experience. To achieve this goal, OPPO has established a robust AI center and engaged in close collaborations with leading global technology companies, such as Google, Microsoft, and MediaTek. OPPO is committed to exploring hybrid mobile AI technologies (on-device and cloud), fostering innovative AI applications on mobile devices. In addition, OPPO frequently participates in leading international AI conferences, sharing its latest AI research findings, maintaining close communication with the AI academic community, and continuously leading the development direction of the industry. In the future, OPPO will continue to put users first, continuously exploring innovative applications of AI technology, to provide users with the ultimate AI phone experience.
