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
Cornell researchers have developed an AI-powered process that automatically transforms a short video of a room into an interactive, 3D simulation of the space.
Jun 30, 2025
0
41
Machine learning & AI
Deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are designed to partly emulate the functioning and structure of biological neural networks. As a result, in addition ...
Hardware
Researchers at the University of Massachusetts Amherst have pushed forward the development of computer vision with new, silicon-based hardware that can both capture and process visual data in the analog domain. Their work, ...
Jun 18, 2025
0
105
Robotics
QUT robotics researchers have developed a new robot navigation system that mimics the neural processes of the human brain and uses less than 10% of the energy required by traditional systems.
Jun 18, 2025
0
109
Robotics
A new, densely annotated 3D-text dataset called 3D-GRAND can help train embodied AI, like household robots, to connect language to 3D spaces. The study, led by University of Michigan researchers, was presented at the Computer ...
Jun 16, 2025
0
70
Computer Sciences
A new explainable AI technique transparently classifies images without compromising accuracy. The method, developed at the University of Michigan, opens up AI for situations where understanding why a decision was made is ...
Jun 13, 2025
0
99
Robotics
Vision-language models (VLMs) are advanced computational techniques designed to process both images and written texts, making predictions accordingly. Among other things, these models could be used to improve the capabilities ...
Hi Tech & Innovation
Researchers at UNIST have developed an AI technology capable of reconstructing three-dimensional (3D) representations of unfamiliar objects manipulated with both hands, as well as simulated surgical scenes involving intertwined ...
Jun 13, 2025
0
40
Machine learning & AI
The ability to precisely predict movements is essential not only for humans and animals, but also for many AI applications—from autonomous driving to robotics. Researchers at the Technical University of Munich (TUM) have ...
Jun 12, 2025
0
46
Engineering
Infrared thermography (IRT) is an effective inspection technique in manufacturing due to its contactless and noninvasive imaging mode. However, existing IRT techniques can only produce 2D results of subsurface structures. ...
Jun 11, 2025
0
21
