Kevin-thu

Epona: Autoregressive Diffusion World Model for Autonomous Driving This repository contains the model checkpoints and test meta data in the paper Epona: Autoregressive Diffusion World Model for Autonomous Driving . 🌏 Project page : https://kevin-thu.github.io/Epona/. It contains four model checkpoints: - `eponanuplan.pkl`: The base world model trained on NuPlan from scratch; - `eponanuplan+nusc.pkl`: The world model finetuned on NuScenes based on the base model; - `eponanuplan+china.pkl`: The world model fintuned on in-house China driving data based on the base model; - `dcaetd20000.pkl`: The temporal-aware DCAE (downsampling rate=32, channel dim=32, temporal patch size=6) fintuned on NuPlan video clips. And two folders of preprocessed json files: - `testmetadatanuplan`: Preprocessed meta infos on NuPlan test set (not including train set); - `metadatanusc`: Preprocessed meta infos on NuScenes train set and validation set.