sniklaus/softmax-splatting
an implementation of softmax splatting for differentiable forward warping using PyTorch
This tool helps researchers and computer vision engineers create smooth, interpolated video frames or images from a sparse set of existing ones. By taking two input images or frames and an estimated optical flow, it generates intermediate frames with improved visual quality, particularly when objects are moving or overlapping. This is useful for anyone working on video processing, motion analysis, or visual effects.
511 stars. No commits in the last 6 months.
Use this if you need to generate high-quality intermediate frames between two existing video frames or images, especially in scenarios with complex motion.
Not ideal if your project requires commercial use, as this implementation is strictly for academic purposes.
Stars
511
Forks
57
Language
Python
License
—
Category
Last pushed
May 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sniklaus/softmax-splatting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HelmchenLabSoftware/Cascade
Calibrated inference of spiking from calcium ΔF/F data using deep networks
adobe/antialiased-cnns
pip install antialiased-cnns to improve stability and accuracy
KaiyangZhou/pytorch-center-loss
Pytorch implementation of Center Loss
devsisters/pointer-network-tensorflow
TensorFlow implementation of "Pointer Networks"
kimhc6028/relational-networks
Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)