This repository has been archived by the owner on Nov 1, 2024. It is now read-only.
Releases: facebookresearch/sound-spaces
Releases · facebookresearch/sound-spaces
Release v0.1.2
- Added task/dataset related code for semantic audio-visual navigation. Data is also updated in the data page.
- Added the baseline SAVi for semantic audio-visual navigation task.
- Added pretrained weights for AV-Nav, AV-WaN, SAVi and they are available here.
- Updated the API to match the latest Habitat version v0.1.7
Release v0.1.1
- Added AV-WaN baseline from this ICLR paper.
- Restrutured codes by moving two baselines into ss_baselines folder and sharing common codes.
- Updated simulator.py to match recent Habitat version (v0.1.6).
release v0.1.0
This version contains the code for our ECCV 2020 paper.
- Introduces the first-of-its-kind audio-visual navigation task
- Creates curated datasets for this task
- Includes ambisonic and binaural RIR renderings for Replica and Matterport environments
- Provides an end-to-end baseline for this task