AI image recognition has now reached a stage where it can accurately identify a wide range of objects in an image. However, the next challenge in this field is to develop an AI capable of interpreting an image for its aesthetic value. The ability of AI to evaluate images in terms of perceived aesthetic quality is often strongly tied to the big data used in training the AI model. As a result, the “opinions” provided by AI are often not to everyone’s taste, and in many cases the models have been shown to have obvious biases. This has led to the development of more refined data and models that take into account the various preferences of different people.
Together with Leida Li, Professor at Xidian University, OPPO Research Institute has come up with the solution to this problem, which is the innovative Personalized Picture Aesthetics Assessment (PIAA) model. The model is the first to optimize the aesthetic evaluation of AI by combining subjective user preferences with more general aesthetic values. The algorithm can perform personalized image ratings based on preferences learned by studying user profiles. Going forward, the model will be used to create personalized experiences for users, not only limited to curating photo albums, but also providing recommendations on how to take the best photo and content that a user might prefer.
OPPO has also chosen to make the PIAA Model Assessment Dataset the open source for developers, with a number of research institutes and universities having already expressed interest in using the data to pursue their own efforts in personalized AI aesthetic evaluation.
In addition to this, OPPO has also offered a multi-view 3D semantic plane reconstruction solution that can accurately analyze surfaces in a 3D environment. The technology can recognize the semantic characteristics of different surfaces, such as floors, desks, and walls, with a much higher degree of accuracy than current single-view reconstruction architecture. Developed in partnership with Tsinghua University, INS-Conv (INcremental Sparse Convolution) can achieve faster and more accurate online 3D instance and semantic segmentation. This can effectively reduce the computing power needed to perform environment recognition, which will allow this technology to be more easily adopted in applications such as automated driving and virtual reality.
OPPO makes AI “light” with a second place in the NAS Challenge
Along with showcasing and discussing the latest research in computer vision and pattern recognition technology, CVPR 2022 also saw a number of technical challenges unfold, with OPPO placing third and above in eight challenges . These include Neural Architecture Research (NAS) Challenge, SoccerNet, SoccerNet Replay Grounding, ActivityNet Temporal Localization, 4th Large-Scale Video Object Segmentation Challenge, ACDC 2022 Challenge on Semantic Segmentation in Adverse visual conditions and WAD Argoverse2 motion prediction.
From mobile photography to automated driving, deep learning models are being applied in a growing pool of industries. However, deep learning relies heavily on big data and computing power and consumes a lot of cost, which presents challenges for its commercial implementation. Neural architecture search (NAS) techniques can automatically discover and implement optimal neural network architectures, reducing reliance on human experience and other inputs to enable truly automated machine learning. In the NAS competition, OPPO researchers trained a supernet of 45,000 neural subnets to inherit supernet parameters by optimizing model parameter forgetting and unfair gradient descent problem, achieving a high level of consistency between subnet performance and performance ranking, ranking second. place among all participants.
Using the NAS technique, researchers only need to train a large supergrid and create a predictor to allow subgrids to learn by inheriting parameters from the supergrid. This provides an efficient and inexpensive approach to obtaining a deep learning model that surpasses those designed manually by expert network architects. This technology can be applied to most of the current artificial intelligence algorithms and can help AI technology that usually requires a large amount of computing power to be implemented on mobile devices by optimizing neural architecture search for look for architects who work well under specific conditions. It will finally bring previously unthinkable levels of AI technology to mobile devices in the near future.
In addition to its success in the NAS Challenge, OPPO also won first place in the SoccerNet Replay Grounding Challenge and third place in the SoccerNet Action Spotting Challenge, after winning second place in both categories at CVPR last year. .
During CPVR 2022, OPPO also participated in seminar presentations and three high-level workshops. During the SLAM seminar, OPPO researcher Deng Fan explained how real-time vSLAM can be performed on smartphones and AR/VR devices. OPPO researcher Li Yikang also spoke at the Mobile AI Seminar and introduced OPPO’s method for performing unsupervised cross-modal hashing between video and text. Named CLIP4Hashing, this method presents an important approach to performing cross-modal research on mobile devices. In the AICITY workshop, Li Wei proposed a motion localization system based on multiple views to identify abnormal driver behavior while driving.
OPPO brings the benefits of AI to more people, sooner
This is the third year that OPPO has participated in CVPR. Over the past three years, AI research has undergone a dramatic shift from developing specific applications like facial recognition to more fundamental technologies that have broader implications.
OPPO’s growing success at CVPR over these three years owes much to its continued investment in AI technology. OPPO began investing in AI development in 2015, creating R&D teams dedicated to language and semantics, computer vision, and other disciplines. In early 2020, the Institute of Intelligent Perception and Interaction was established under the OPPO Research Institute to further OPPO’s exploration of cutting-edge AI technologies. Today, OPPO has more than 2,650 global patent applications in the field of AI, covering computer vision, speech technology, natural language processing, machine learning and more.
Guided by its brand proposition, “Inspiration Ahead”, OPPO is also working with industry partners to bring AI technology from the lab to everyday life. In December 2021, OPPO launched its first self-developed dedicated imaging NPU, MariSilicon X. The NPU offers both powerful computing performance and high power efficiency to enable complex AI algorithms to be executed at unprecedented speeds on mobile devices, delivering superior video quality through advanced technologies. night video and other image processing algorithms. OPPO’s AI technology has also been used to develop products and features such as CybeReal real-time spatial AR generator, OPPO Air Glass, Omoji, and more. Through these technologies, OPPO aims to create more realistic digital worlds that combine virtual and reality to create brand new experiences for users.
MENAFN22062022005728012573ID1104417998
.