Comments (2)
That may be a bug after refactor, I will check the details. The usage about these two lines is to estimate accurate optical flows. Since we adopt RAFT for flow estimation, we noticed the performance of deep learning-based optical flow estimation methods is related to the frame resolution. If the resolution is too low, the performance of flow estimation will degrade. Therefore, we enlarge the frame resolution when the resolution is too low.
from fgt.
This bug is fixed, I impose the resize operations to optical flows in calculate_flow
function in the code ./tool/video_inpainting.py
.
from fgt.
Related Issues (20)
- How to fine-tune FGT on my own dataset HOT 2
- Run on image HOT 2
- What is the GPU model used in the experiment? HOT 2
- T dimension problems in encoders HOT 4
- Questions about the correspondence between the published pre-trained models and the algorithms in the paper. HOT 3
- FGT++ HOT 5
- output video size HOT 3
- The flow propagation HOT 3
- About square mask settings HOT 1
- Add a way to extract an `ONNX` file HOT 1
- Cuda OOM (1k+ frame video) on A100 HOT 4
- supplementary material HOT 2
- Constantly getting 'ValueError: need at least one array to stack' error
- Not inpainting beginning and end of videos
- Can't be cleaned up, is it an issue with the pre-trained model? HOT 4
- Which one is better? FGT or ISVI? HOT 2
- Outpainting Training on Custom Data
- Watermark removal results is worse
- CUDA error HOT 1
- Slow speed when inferencing HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fgt.