OmniShotCut is a sensitive and more informative SoTA for Shot Boundary Detection.
OmniShotCut can detect shot changes of the video in diverse sources (anime, vlog, game, shorts, sports, screen recording, etc.), and recognize Sudden Jump and Transitions (dissolve, fade, wipe, etc.) by proposing a Shot-Query-based Video Transformer.
🔥 Update | 👀 Visualization | 🔧 Installation | 🐍 Quick Start | ⚡ Inference | 💻 OmniShotCut Benchmark
- Release ArXiv paper
- Release the inference weights
- Release Gradio demo (with online)
- Release 'pip install omnishotcut' version
- Release the benchmark
- Release the training code and curation
⭐ If you like OmniShotCut, please help ⭐⭐star⭐⭐ this repo. Thanks! 🤗
First install PyTorch with CUDA support, and make sure a working ffmpeg binary is
on your PATH (used for video decoding; e.g. conda install -c conda-forge ffmpeg).
Then install OmniShotCut:
pip install git+https://github.com/UVA-Computer-Vision-Lab/OmniShotCut.gitOnce installed, running shot boundary detection is just a few lines:
import omnishotcut
# Load model — accepts a local checkpoint path or HuggingFace repo
cut_model = omnishotcut.load("uva-cv-lab/OmniShotCut", filename = "OmniShotCut_ckpt.pth")
# Run on a video file
ranges = cut_model.inference("video.mp4", mode="clean_shot")ranges is a list of [start_frame, end_frame] pairs for each detected shot.
By default mode="clean_shot" returns only clean cuts (no transitions).
Use mode="default" to also get dissolves, wipes, and fades with their labels:
ranges, intra_labels, inter_labels = cut_model.inference("video.mp4", mode="default")Besides video file paths, inference() also accepts numpy arrays and torch tensors directly — both (T, H, W, 3) RGB (either uint8, or float in [0, 1]). The input H/W can be arbitrary; frames are resized to the model's process resolution automatically, so results match the video-file path:
ranges = cut_model.inference(frames_thwc, mode="clean_shot") # frames_thwc: (T, H, W, 3)conda create -n OmniShotCut python=3.10
conda activate OmniShotCut
conda install -c conda-forge ffmpeg # required: frame-accurate video decoding backend
pip install -r requirements.txt
pip install -e .Note: video decoding uses
ffmpeg(viaffmpeg-python), so a workingffmpegbinary must be on yourPATH. Installing it fromconda-forgeas above is the most reliable way to get one with all shared libraries present.
Local Gradio can be created by simply running the following:
python app.py Click "Running on public URL".
This section presents more formal fun and controllable setting in running.
First, let us download the checkpoint
mkdir checkpoints
cd checkpoints
wget https://huggingface.co/uva-cv-lab/OmniShotCut/resolve/main/OmniShotCut_ckpt.pthWe provide some modes for the inference. 'default' mode will shot the intra and inter label we define. However, we believe that most users might want the most direct results, which is the general shots without any transitions. To this end, please use '--mode clean_shot'.
Execute the inference by:
python inference.py --checkpoint_path checkpoints/OmniShotCut_ckpt.pth --input_video_path __assets__/demo_video1.mp4 --overlap_window_length 20 --mode defaultResults are saved to results.json. Visualization is saved to demo_video_results/, where vertical bars with the same color indicate the same shot.
@article{wang2026omnishotcut,
title={OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer},
author={Wang, Boyang and Xu, Guangyi and Tang, Zhipeng and Zhang, Jiahui and Cheng, Zezhou},
journal={arXiv preprint arXiv:2604.24762},
year={2026}
}