تقرير
CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting
| العنوان: | CARFF: Conditional Auto-encoded Radiance Field for 3D Scene Forecasting |
|---|---|
| المؤلفون: | Yang, Jiezhi, Desai, Khushi, Packer, Charles, Bhatia, Harshil, Rhinehart, Nicholas, McAllister, Rowan, Gonzalez, Joseph |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | 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. Comment: ECCV 2024. Project page with video and code: www.carff.website |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2401.18075 |
| رقم الأكسشن: | edsarx.2401.18075 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |