Light

google / layered-scene-inference Goto Github PK

View Code? Open in Web Editor NEW

86.0 6.0 20.0 144 KB

Code accompanying the paper "Layer-structured 3D Scene Inference via View Synthesis", ECCV 2018

Home Page: https://shubhtuls.github.io/lsi/

License: Apache License 2.0

Python 98.63% MATLAB 1.37%

3d-vision computer-vision layered-depth-images deep-learning

layered-scene-inference's Introduction

Layer-structured 3D Scene Inference via View Synthesis

This code accompanies the paper

Layer-structured 3D Scene Inference via View Synthesis
Shubham Tulsiani, Richard Tucker, Noah Snavely
In ECCV, 2018.

Please note that this is not an officially supported Google product.

Project Page

This is the initial release of the Layered Scene Inference TensorFlow code for learning to infer layered depth images (LDIs) from single input views via multi-view supervision.

Training and Evaluating

You'll first need to follow the installation instructions. To subsequently train and evaluate the LDI prediction models, see the documentation for running experiments using the Synthetic or KITTI datasets.

Citation

If you use this code for your research, please consider citing:

@inProceedings{lsiTulsiani18,
  title={Layer-structured 3D Scene Inference via View Synthesis},
  author = {Shubham Tulsiani
  and Richard Tucker
  and Noah Snavely},
  booktitle={ECCV},
  year={2018}
}

layered-scene-inference's People

Contributors

Stargazers

Watchers

Forkers

alakia zhengqili shubhampachori12110095 mtlong sagacious-cao yazici jtpils jarygrace wangjingbo1219 hityzy1122 tedyhabtegebrial luisdecker neotim lijx10 jasonlsc isabella232 youngat19 ghas-results

layered-scene-inference's Issues

Some coordinates will fall outside the image area during forward splat

Hi, thanks to your work, it is great while I have some puzzles.
During forward splat, we can compute the target coordinates according to the camera intrinsic and extrinsic. After that we can compute a target image using the source image values and the target coordinates. But the target coordinates may exceed the image area and the target image will have no values in those areas, especially in the initial stage of training. In extreme cases, the whole image will not receive any value from the original image and will not provide any gradient in loss operation.
I want to know how you deal with this problem? The paper says "To overcome this, we simply render the target frame at half the input resolution, i.e. the output image from the rendering function described in Section 3.2 is half the size of the input LDI". Why half resolution can solve this problem?

Simple test

Are there any pretrained models for simple test on KITTI?

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.