Comments (1)
Hi.
- The difference is the sequence of creating patches and estimation.
To generate the ground_truth fake; First, we are estimating the whole RGB image's depth and then create patches out of the estimated depth(although we are using a higher resolution than default Midas we made sure estimations are consistent in terms of overall depth structure to be used as fake ground truth).
The inner data is generated the opposite way. First, we are creating patches and then feeding them to the Midas. This way we will have much more details but the results will have inconsistent overall structure.
outer data is generated the same way as ground truth fake but at the default Midas resolution.
This way and by using some filtering tricks we are able to mimic the characteristics of data we need to train a depth merge operation. I recommend reading the supplementary material as we are discussing the process of dataset generation and filtering in more detail.
- Mergenet has one function: Merging details (high frequencies) to a base(low frequency) depth map. This functionality can be used for both double estimation and merging patches to the base process since in both cases there is a low frequency and a high-frequency depth that we want to merge. (Low/High estimates for double estimation and Base/Patch for the latter).
from boostingmonoculardepth.
Related Issues (20)
- GPU thresh hold for nvidia A100 ?? HOT 2
- RuntimeError: The size of tensor a (75) must match the size of tensor b (76) at non-singleton dimension 3 HOT 4
- Code section2 error HOT 5
- Temporal inconsistency on image sequences HOT 4
- Can we use this for video input? HOT 1
- Issue max res 720 * 1280 ? HOT 8
- How to speed up the inference? HOT 2
- License of output images HOT 2
- Feature Request: Run on CPU or MPS for Apple M1/M2 HOT 4
- Unable to download mergenet model weights HOT 2
- Bit depth and banding HOT 2
- Which one of MiDas, DPT and LeRes is better for monocular depth estimation and takes the shortest time? HOT 1
- What's the parameter to be set in demo.py for "(NEW!) Now you can set the maximum resolution of the results to reduce runtime" HOT 1
- Why does NAN appear in the model inference process HOT 2
- Depth map by LeRes HOT 1
- LeRes weights download link is not working HOT 1
- How to align estimated depth with GT depth? HOT 1
- Colab error: FileNotFoundError: [Errno 2] No such file or directory: 'res101.pth' HOT 1
- Colab error: FileNotFoundError: [Errno 2] No such file or directory: './pix2pix/checkpoints/mergemodel/latest_net_G.pth' HOT 8
- no NVIDIA driver found error 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 boostingmonoculardepth.