Based on the foundation of proprietary technologies and SenseCore AI infrastructure, SenseTime has rapidly opened up AI application in multiple vertical scenarios, and is empowering various industries.
Adhering to originality, SenseTime Research is one of the most prolific contributors of AI related papers in the research community. SenseTime Research has cooperated with dozens of top universities and research institutions internationally. The successful research collaborations between academia and industry have applied high-quality research to the real world and established an effective talent cultivation mechanism.
SenseFoundry Enterprise is our software platform to facilitate and accelerate the digital transformation of our enterprise customers, addressing complex demands from different industry verticals.
SenseFoundry is a one-stop software platform tailored for Smart City management, addressing the needs of customers in the public sector.
SenseME software platform offers a full suite of products including SDKS, AI sensors and ISP chips, and enables a broad range of IoT devices to facilitate perceptial intelligence and content enhancement.
Our SenseMARS software platform serves as the key enabling technology platform for the Metaverse to create new life experiences.
Sensetime Education builds a leading AI education system in line with the national development strategy.
Move Smart with AI
01 / 06
2D/3D key points of face/body/gesture can be captured and tracked in various situations, e.g., darkness, occlusion, tricky angles and exaggerated expressions. The technique can be utilized for rendering special effects in the post processing.
02 / 06
By detecting the 3D key points of face/body/hand, the SDK can drive the expressions/body movements/gestures for 2D/3D avatar. Additionally, it works well for multiple expressions and complex movements.
03 / 06
2D/3D key point detection and tracking for body (hands/feet) and post-rendering, it can realize the effect of virtual manicure and virtual shoe fitting. Furthermore, it has a robust visualization under complex situations such as different light intensities and occlusion.
04 / 06
Fast customized generation of animatable photorealistic 2D real speaker and 3D virtual character assets, and vivid animation driven by audio with deep neural network. Also support human machine interaction with advanced mult-modal algorithms.
05 / 06
Style transfer can convert the face in real-time video or high-resolution pictures to a specific style of portrait, including Japanese manga style, CG style, hand-painted style, etc.
06 / 06
Based on image generation technologies such as generative adversarial network, it can edit pictures/videos in detail, and support downstream tasks such as makeup editing, hair editing, motion transfer, etc.
01 / 06
2D/3D key points of face/body/gesture can be captured and tracked in various situations, e.g., darkness, occlusion, tricky angles and exaggerated expressions. The technique can be utilized for rendering special effects in the post processing.
02 / 06
By detecting the 3D key points of face/body/hand, the SDK can drive the expressions/body movements/gestures for 2D/3D avatar. Additionally, it works well for multiple expressions and complex movements.
03 / 06
2D/3D key point detection and tracking for body (hands/feet) and post-rendering, it can realize the effect of virtual manicure and virtual shoe fitting. Furthermore, it has a robust visualization under complex situations such as different light intensities and occlusion.
04 / 06
Fast customized generation of animatable photorealistic 2D real speaker and 3D virtual character assets, and vivid animation driven by audio with deep neural network. Also support human machine interaction with advanced mult-modal algorithms.
05 / 06
Style transfer can convert the face in real-time video or high-resolution pictures to a specific style of portrait, including Japanese manga style, CG style, hand-painted style, etc.
06 / 06
Based on image generation technologies such as generative adversarial network, it can edit pictures/videos in detail, and support downstream tasks such as makeup editing, hair editing, motion transfer, etc.
Return
