Neural Network Architectures for Images
Explore neural network architectures for image processing, including classification, segmentation, and enhancement. Learn about CNNs, ResNets, autoencoders, and their applications in various imaging tasks.
Unlearned Neural Networks as Image Priors for Inverse Problems
Explore unlearned neural networks as image priors for inverse problems in imaging, covering Deep Image Prior, Deep Decoder, and Deep Geometric Prior techniques and their applications.
Keras Convolutional Neural Networks for MNIST and Fashion MNIST
Explore convolutional neural networks for image processing, focusing on MNIST and Fashion MNIST datasets. Learn about CNN architecture, training, and evaluation for advanced deep learning applications.
Integral Images: Concept and Application in Spatial Algorithms
Learn about integral images for faster spatial partitioning and search algorithms, with a demonstration of object tracking implementation and practical coding examples.
Deep Learning for Vision: Tricks of the Trade
Explore deep learning's evolution in computer vision, from unsupervised algorithms to modern object recognition systems. Learn practical tips and future challenges in this field.
In-memory Computing and Dynamic Vision Sensors for Internet of Video Things
Exploring neuromorphic technologies, dynamic vision sensors, and in-memory computing for energy-efficient IoT video applications, with focus on innovative solutions for intelligent transportation and unattended ground sensors.
Applied Deep Learning in Speech Recognition and Collaborative Filtering - Session 5
Explore cutting-edge AI applications in speech recognition and collaborative filtering systems, featuring NVIDIA Research insights from NeurIPS 2018.
Improving Energy Efficiency and Robustness of tinyML Computer Vision Using Log-Gradient Input Images
Explore innovative techniques to enhance energy efficiency and robustness in tinyML computer vision, focusing on log-gradient input images and architecture optimization for microcontrollers.
Towards Software-Defined Imaging - Adaptive Video Subsampling for Energy-Efficient Object Tracking
Explore adaptive video subsampling for energy-efficient object tracking using software-defined imaging algorithms and CMOS sensors' ROI capabilities, with FPGA-accelerated implementations.
Recent Progress on TinyML Technologies and Always-On Machine Opportunities
Explore recent advancements in tinyML technologies, their implementation, and potential applications across various industries, with a focus on always-on machine learning for voice, vision, and sensing.
Driving with Attention
Explore innovative sensor fusion techniques for autonomous driving, focusing on TransFuser and NEAT models that leverage attention mechanisms to improve perception and decision-making in complex traffic scenarios.
ROB 2018 - Eddy Ilg- Occlusions, Motion and Depth Boundaries with a Generic Network
Explore cutting-edge techniques in computer vision, focusing on occlusions, motion, and depth boundaries using a generic network architecture for improved multiview stereo results.
Using the GPU to Create a Seamless Display from Multiple Projectors - SIGGRAPH 2011
Explore GPU-based techniques for creating seamless multi-projector displays, covering warp blending, SLI Mosaic, and Nvidia's API for scalable desktop and command systems.
Tools for Mobile Photography and Computer Vision
Explore computational photography and computer vision for mobile devices, covering NVIDIA's research, hardware developments, and software tools like OpenCV and FCam for innovative mobile applications.
Visual AI in Milliwatts - A Grand Challenge and Massive Opportunity
Explore visual AI's potential in low-power devices, discussing challenges, opportunities, and applications in security cameras and beyond. Learn about deep learning, processors, and algorithms driving this technology.
Build Your Own AI Assistant - Object Classification with Python
Learn to build an AI assistant using Python, TensorFlow, and Google Colab for object classification. Covers neural networks, image processing, and hands-on demos for practical implementation.
TinyML Vision Challenge - Summit 2021
Discover the tinyML Vision Challenge: Create innovative computer vision applications using tinyML, compete for $6k in prizes, and gain recognition from the tinyML Foundation.
Stable Diffusion DreamBooth Guide - Optimal Classification Images Count Comparison Test
Comprehensive guide on optimizing DreamBooth training in Automatic1111, comparing classification image counts for best results in AI image generation and fine-tuning.
Filters and Other Potions for Early Vision and Recognition
Explore early vision and recognition techniques, including filters, deep networks, and multiscale processing. Learn about spacetime oriented filters and tensor factorization for improved visual analysis.
Automated Background Removal Using PyTorch - Wehkamp's Image Processing Pipeline
Discover an automated pipeline for efficient background removal in product images using PyTorch and machine learning, enhancing visual experiences for e-commerce customers.
Visual Rendering Techniques - Session 26
Explore advanced techniques in visual rendering, covering cutting-edge methods for creating realistic and immersive digital imagery in various applications.