Comments (5)
Hi we directly use sparse GT.
from unimatch.
Thanks for the quick reply!
Then with sparse GT, do you mask out the invalid pixels for loss calculation? Or you use other ways to compensate the difference between dense map and sparse map?
Another question is that do you feel with less pixel GT guidance, the results accuracy reduced? In other words, do you think it's always better to have denser GT; or up to certain point, the density of GT doesn't make too much difference anymore?
Thanks for your time!
from unimatch.
Yes, invalid pixels are masked out.
I feel denser GT would lead to better performance, but haven't conducted such comparisons thus I am not absolutely certain. To verify this, you might want to subsample the dense GT (e.g., on Scene Flow dataset) for training and see how the performance varies. This is an interesting question and I would also be happy to hear your findings if you are interested in doing such comparisons in future, thanks!
from unimatch.
Thanks! Yeah I will do some experiments about it. Can I have the configs of your training to reproduce the numbers in the paper regarding argoverse? Also, the final output after the fine-tuning is still dense or eventually it becomes sparse or has only valid values for sparse region? Wondering if the dense performance from the pretrained network can still be carried out in the fine tuning stage by some implicit interpolation of the network even though using sparse GT; or with more epochs, it sooner or later will regress to absolute sparse output.
Eventually I want to input sparse but get dense output, not sure if such performance can be achieved by leveraging a dense pretrained model + fine-tune on sparse data directly, or I must add the explicit interpolation module into the network. Thanks!
from unimatch.
From my experiments on argoverse dataset, the final predictions will be less reliable on regions that don't have ground truth supervison (e.g., the sky, similar phenomenon can also be observed from visual results on KITTI dataset). So if the model is finally finetuned with sparse GT, this problem might also occur even the model is pretrained on dense GT data.
from unimatch.
Related Issues (20)
- About weights HOT 2
- is this method suitable for panoramas which is about up and down?? HOT 1
- nice work! and plan to live camera gui? HOT 2
- Resetting hidden state during refinement HOT 2
- Running in Windows? HOT 1
- Why the value of optical flow is opposite? HOT 1
- gmstereo_scale1 vs gmstereo_scale2 Inference speed HOT 1
- Decoding RGB Optical Flow for Motion Information Extraction in Video Action Recognition HOT 3
- What is the best resolution for inferencing optical flow? HOT 4
- The optical flow between two identical images looks like random noise. Is this normal? HOT 2
- Request for new weights HOT 1
- gmstereo_scale1_train.sh HOT 1
- The problem of optical flow prediction HOT 1
- unimatch.py line 257 HOT 1
- [GMflow] What do the ’train_dataset ‘ equation coefficients mean when stage=sintel? HOT 1
- Question about model and model_without_ddp HOT 2
- loss curve HOT 2
- Question on upsampling during training. HOT 4
- tartan air dataset HOT 5
- About disparity and depth HOT 2
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 unimatch.