Concept

Computer stereo vision

Related lectures (32)

Covers an internship report at Tencent Al lab, focusing on 3D avatar reconstruction and neural rendering techniques.

Thermal Comfort Monitoring: Non-Intrusive Solutions

Presents a framework for non-intrusive thermal comfort monitoring using computer vision and machine learning techniques.

Fine-Grained Visual Categorization: Challenges and Solutions

Explores challenges and solutions in fine-grained visual categorization, focusing on computer vision and machine learning.

Grant Writing: Conclusion

Covers the final steps of the grant proposal process and emphasizes the importance of following guidelines and using a persuasive writing style.

Geometric Stereo: Depth Recovery Techniques Log in to Mediaspace to watch this video

Discusses geometric stereo principles and depth recovery techniques using stereo vision methods.

Shape from Stereo-1 Log in to Mediaspace to watch this video

Explores geometric stereo, epipolar geometry, correlation methods, occlusions, and real-time implementation challenges in stereo vision systems.

Shape From Stereo-2 Log in to Mediaspace to watch this video

Explores stereo vision concepts such as occlusions, window size impact, multi-view stereo, dynamic shape reconstruction, and graph-based segmentation.

Synthetic Training Data via Generative Models Log in to Mediaspace to watch this video

Explores the benefits of synthetic data in computer vision through generative models mimicking real images with low sim2real gap.

Course Project Choice Log in to Mediaspace to watch this video

Introduces the course project for CS-503, emphasizing the importance of project selection related to vision and perceptual agents.

Delineation: Techniques and Dynamics Log in to Mediaspace to watch this video

Explores techniques for delineating objects in images, including dynamic programming and live wire methods.

Visual Intelligence: Machines and Minds Log in to Mediaspace to watch this video

Explores the history and techniques of computer vision, covering image formation, transformation, dynamic perspectives, and 3D estimation cues.

Shape from Shading: Recovering 3D Information from 2D Images Log in to Mediaspace to watch this video

Covers the techniques for recovering 3D shape information from 2D images using shading models and modern deep learning approaches.

Edge Detection: Deep Learning Insights Log in to Mediaspace to watch this video

Explores the evolution of edge detection techniques, from Canny to deep learning insights.

Shape from Contours Log in to Mediaspace to watch this video

Explores shape reconstruction from contours using edge-based stereo matching and visual hull techniques for accurate 3D reconstruction.

Visual Intelligence: Projects and Challenges Log in to Mediaspace to watch this video

Explores projects and challenges in visual intelligence, including hands-on learning and analysis of vision methods.

Machine Learning for Feature Extraction Log in to Mediaspace to watch this video

Explores machine learning for feature extraction, 3D vision, and neural networks in mobile robotics.

Depth Perception: Monocular and Binocular Cues Log in to Mediaspace to watch this video

Covers depth perception, focusing on monocular and binocular cues, including motion parallax and stereoscopic vision.

Visual Intelligence: Machines and Minds Log in to Mediaspace to watch this video

Explores visual intelligence, covering image formation, perception, computer vision, correspondence learning, motion analysis, and recognition in videos.

Robust Vision: Data Augmentation and Ensembling Techniques Log in to Mediaspace to watch this video

Explores data augmentation and ensembling techniques for robust vision, comparing ViT and ResNet models.

Computer Vision: Recap Log in to Mediaspace to watch this video

Recaps key concepts in computer vision, challenges, opportunities, and upcoming exam details.