CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting

We propose CARFF, a method for predicting future 3D scenes given past observations. Our method maps 2D ego-centric images to a distribution over plausible 3D latent scene configurations and predicts the evolution of hypothesized scenes through time. Our latents condition a global Neural Radiance Fie...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-07
Main Authors: Yang, Jiezhi, Desai, Khushi, Packer, Charles, Bhatia, Harshil, Rhinehart, Nicholas, McAllister, Rowan, Gonzalez, Joseph
Format: Article
Language:English
Subjects:
Coding
Contingency
Forecasting
Markov processes
Multiagent systems
Radiance
Representations
Three dimensional models
Trajectory planning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose CARFF, a method for predicting future 3D scenes given past observations. Our method maps 2D ego-centric images to a distribution over plausible 3D latent scene configurations and predicts the evolution of hypothesized scenes through time. Our latents condition a global Neural Radiance Field (NeRF) to represent a 3D scene model, enabling explainable predictions and straightforward downstream planning. This approach models the world as a POMDP and considers complex scenarios of uncertainty in environmental states and dynamics. Specifically, we employ a two-stage training of Pose-Conditional-VAE and NeRF to learn 3D representations, and auto-regressively predict latent scene representations utilizing a mixture density network. We demonstrate the utility of our method in scenarios using the CARLA driving simulator, where CARFF enables efficient trajectory and contingency planning in complex multi-agent autonomous driving scenarios involving occlusions.
ISSN:2331-8422