Computational 3D vision concerns algorithms and sensor systems that infer three-dimensional structure, motion, and semantics from visual and related signals. Methods span monocular and multi-view 3D reconstruction, depth estimation, inverse rendering, and 4D scene capture, often integrating LiDAR, radar, infrared, and event or neuromorphic sensors. Deep learning architectures and data-driven simulation play central roles in segmentation, pose estimation, anomaly detection, and novel view synthesis, enabling robust perception, mapping, and editing of complex environments for robotics, autonomous systems, and immersive displays.
Computer Sciences
A study from EPFL reveals why humans excel at recognizing objects from fragments while AI struggles, highlighting the critical role of contour integration in human vision.
Jul 22, 2025
0
234
Engineering
Complex tubes with flanges, joints and other components, characterized by a large number of diverse shapes and complex structures, are key parts of aircraft engines, rockets and other equipment. In order to ensure the smooth ...
Jul 21, 2025
0
23
Automotive
A new data-driven technique for obstacle avoidance in autonomous vehicles is reported in the International Journal of Vehicle Design. The approach might overcome many of the longstanding challenges in the development of self-driving ...
Jul 21, 2025
0
26
Engineering
Researchers at The University of Osaka have developed a novel framework for measuring occupancy in open-plan offices with unprecedented precision. This innovative system uses computer vision and AI to analyze occupancy at ...
Jul 14, 2025
0
30
Computer Sciences
Over the past years, computer scientists have introduced increasingly sophisticated generative AI models that can produce personalized content following specific inputs or instructions. While image generation models are now ...
Machine learning & AI
An advanced artificial intelligence (AI) technology has been developed that can extract three-dimensional (3D) spatial structure and object information within indoor environments using just a single 360-degree panoramic photograph. ...
Jul 9, 2025
0
28
Engineering
A research team from the Aerospace Information Research Institute (AIR) of the Chinese Academy of Sciences has developed a novel method to generate highly detailed three-dimensional (3D) city models using radar data, addressing ...
Jul 9, 2025
0
30
Robotics
Conventional robots, like those used in industry and hazardous environments, are easy to model and control, but are too rigid to operate in confined spaces and uneven terrain. Soft, bio-inspired robots are far better at adapting ...
Security
Researchers have demonstrated a new way of attacking artificial intelligence computer vision systems, allowing them to control what the AI "sees." The research shows that the new technique, called RisingAttacK, is effective ...
Jul 1, 2025
0
159
Robotics
A new imaging technique developed by MIT researchers could enable quality-control robots in a warehouse to peer through a cardboard shipping box and see that the handle of a mug buried under packing peanuts is broken.
Jul 1, 2025
0
62
