paper-with-me

Papers

DIO: Decomposable Implicit 4D Occupancy-Flow World Model

2025-01-01 · CVPR 2025 1 · Christopher Diehl, Quinlan Sykora, Ben Agro, Thomas Gilles, Sergio Casas, Raquel Urtasun

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

model

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

SelfOccFlow: Towards end-to-end self-supervised 3D Occupancy Flow prediction

2026-02-27 · Xavier Timoneda, Markus Herb, Fabian Duerr, Daniel Goehring arxiv

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 Driving

Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving

2023-08-02 · CVPR 2023 1 · Ben Agro, Quinlan Sykora, Sergio Casas, Raquel Urtasun

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 Forecasting

StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation

2023-02-19 · CVPR 2024 1 · Yining Shi, Kun Jiang, Ke Wang, Jiusi Li 외

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 Fusion

Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics

2019-10-01 · ICCV 2019 10 · Michael Niemeyer, Lars Mescheder, Michael Oechsle, Andreas Geiger

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 reconstruction

D$^2$-World: An Efficient World Model through Decoupled Dynamic Flow

2024-11-26 · Haiming Zhang, Xu Yan, Ying Xue, Zixuan Guo 외

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…