TransNetV2 — Deep Shot Boundary Detector

Description

Deep 3D-CNN shot boundary/scene-cut detector, SOTA on ClipShots/BBC/RAI with real-time inference.

URL

• Visit resource

Related resources

• MDLSeg: Parameter-Free Video Scene Segmentation via Minimum Description LengthAcademic paper proposing a parameter-free scene-segmentation method claimed to outperform PySceneDetect.
• SceneSegmentation-SCRLOfficial PyTorch implementation of CVPR 2022 Scene Consistency Representation Learning for movie-level scene segmentation (MovieNet/SceneSe…
• BackgroundMattingV2Real-time high-resolution background matting requiring a captured background plate, achieving 4K 30fps on RTX 2080 Ti, companion to arXiv:2…
• RobustVideoMattingReal-time human video matting via recurrent neural network requiring no green screen, achieving 4K 76FPS on GTX 1080 Ti, companion to arXiv…
• DQ-Ladder: Deep Q-Network Time/Quality-Aware Bitrate LadderDeep reinforcement learning (DQN) approach to bitrate ladder construction achieving 10.3%+ BD-rate gain and 22% decode-time reduction.
• Evaluating Video Quality Metrics for Neural and Traditional Codecs (4K/UHD-1)Academic comparison of VMAF, AVQBits, and FasterVQA no-reference quality metrics on 4K content.
• Bitrate Ladder Construction via Transfer Learning and Spatio-Temporal FeaturesML-based bitrate ladder optimization achieving 94.1% complexity reduction at only 1.71% BD-rate cost using transfer learning.
• VMAF-torchPyTorch reimplementation of VMAF metric, GPU/gradient-friendly for use in learned codec optimization loops.
• CompressedVQA: Full/No-Reference VQA for Compressed UGC VideoICME 2021 grand challenge-winning full-reference and no-reference video quality models for compressed user-generated content.
• 2BiVQA: Double Bi-LSTM No-Reference Video Quality AssessmentNo-reference VQA model for UGC video using double Bi-LSTM, companion code to arXiv:2208.14774.