Comments (2)
For reference the paper mentions this:
We connect each patch to every frame within distance r
from the frame index the patch was extracted. This means
that when a new patch is added, we add edges between that
patch and the previous r keyframes. When a new frame is
added, we add edges between each patch extracted in the
last r keyframes with the new frame.
It seems unclear whether new patches are connected to the last r keyframes, or connected to keyframes within distance r of the current frame. Regardless my bug just seems to be related to having too long of a video and having a number of keyframes that exceeds the buffer size allocated.
from dpvo.
It seems unclear whether new patches are connected to the last r keyframes, or connected to keyframes within distance r of the current frame.
Every incoming frame is treated as a keyframe, so in the case of DPVO these are the same
from dpvo.
Related Issues (20)
- what part of the tartan dataset being used for training?
- Running in c++?
- About camera pose for Replica HOT 4
- scale drift on demo
- Compiling in Windows HOT 10
- Points not visible in DPViewer HOT 2
- How is TarTanAir dataset downloaded? HOT 2
- Run demo.py, while only loops twice and ends HOT 16
- Regarding the issue of deep initialization
- metric depth estimation
- Is running in CPU only possible?
- How is the structure of the Tartan datasets arranged during training? HOT 2
- NAN appears when training HOT 1
- Scheduler issue during training
- About coordinate system
- Trajectory Saving Error + make_traj HOT 1
- Regarding the issue of DPVO running result fluctuations
- ValueError: all input arrays must have the same shape HOT 1
- demo.py
- Can't run on ubunut 24.04
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 dpvo.