2 रिपॉजिटरी
Processes multiple video frames simultaneously in batches to maximize GPU throughput and reduce per-frame overhead.
Distinct from Batch Video Processing: Distinct from Batch Video Processing: focuses on the pipeline architecture for frame-level batching, not general multi-file workflows.
Explore 2 awesome GitHub repositories matching graphics & multimedia · Batch Frame Processing Pipelines. Refine with filters or upvote what's useful.
Squirrel-RIFE is a GPU-accelerated video processing tool that uses a neural network to generate intermediate frames between existing video frames, enabling smooth slow-motion effects and frame rate conversion. It is built around the RIFE (Real-Time Intermediate Flow Estimation) model, which analyzes motion between consecutive frames to predict and insert new frames, and leverages NVIDIA CUDA for parallel processing to achieve high-speed inference. The tool distinguishes itself by combining neural frame interpolation with practical video preprocessing features, including pixel-level duplicate
Processes multiple video frames simultaneously in batches to maximize GPU throughput and reduce per-frame overhead.
This project is a deep learning framework built for detecting and tracking human body keypoints in images and video streams. It functions as both a real-time motion tracking system and a machine learning environment for training and evaluating pose estimation models. The system utilizes a two-branch convolutional neural network to predict body part locations and their directional connections simultaneously. It employs multi-stage feature refinement to improve keypoint localization accuracy and uses greedy parsing and bipartite matching algorithms to associate detected parts into individual sk
Executes parallel tensor-based batch processing to maintain high frame rates during real-time video analysis.