Skip to content
Code accompanying the paper "Layer-structured 3D Scene Inference via View Synthesis", ECCV 2018
Branch: master
Clone or download
Latest commit 59b5d37 Aug 9, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
docs generic path defaults Aug 7, 2018
external kitti instructions Aug 4, 2018
lsi Clarifying flag descriptions in additional files. Aug 9, 2018
.gitignore absl instead of pyglib Jul 30, 2018
CONTRIBUTING.md initial import Mar 12, 2018
LICENSE initial import Mar 12, 2018
README.md Edits to README.md Aug 9, 2018
ldi_enc_dec.py Clarifying flag descriptions. Aug 9, 2018
ldi_pred_eval.py Clarifying flag descriptions. Aug 9, 2018

README.md

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}
}
You can’t perform that action at this time.