DIO: Decomposable Implicit 4D Occupancy-Flow World Model
We present DIO, a flexible world model that can estimate the scene occupancy-flow from a sparse set of LiDAR observations, and decompose it into individual instances. DIO can not only complete instance shapes at the present time, but also forecast their occupancy-flow evolution over a future horizon. Thanks to its flexible prompt representation, DIO can take instance prompts from off-the-shelf models like 3D detectors, achieving state-of-the-art performance in the task of 4D semantic occupancy completion and forecasting on the Argoverse 2 dataset. Moreover, our world model can easily and effectively be transferred to downstream tasks like LiDAR point cloud forecasting, ranking first compared to all baselines in the Argoverse 4D occupancy forecasting challenge.
Code (0)
등록된 구현이 없습니다.
Tasks
modelMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SelfOccFlow: Towards end-to-end self-supervised 3D Occupancy Flow prediction
Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely…
Autonomous DrivingImplicit Occupancy Flow Fields for Perception and Prediction in Self-Driving
A self-driving vehicle (SDV) must be able to perceive its surroundings and predict the future behavior of other traffic participants. Existing works either perform object detection followed by trajectory forecasting of t…
Future predictionobject-detectionObject DetectionTrajectory ForecastingStreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation
Predicting the future occupancy states of the surrounding environment is a vital task for autonomous driving. However, current best-performing single-modality methods or multi-modality fusion perception methods are only …
Autonomous DrivingSensor FusionOccupancy Flow: 4D Reconstruction by Learning Particle Dynamics
Deep learning based 3D reconstruction techniques have recently achieved impressive results. However, while state-of-the-art methods are able to output complex 3D geometry, it is not clear how to extend these results to t…
3D geometry3D Reconstruction4D reconstructionD$^2$-World: An Efficient World Model through Decoupled Dynamic Flow
This technical report summarizes the second-place solution for the Predictive World Model Challenge held at the CVPR-2024 Workshop on Foundation Models for Autonomous Systems. We introduce D$^2$-World, a novel World mode…