DIO: Decomposable Implicit 4D Occupancy-Flow World Model
Christopher Diehl, Quinlan Sykora, Ben Agro, Thomas Gilles, Sergio Casas, Raquel Urtasun
2025Year
Abstract
Scene Occupancy (b) Instance Occupancy (c) Scene Flow (d) Rendered LiDAR Figure 1. We present DIO, a world model that learns unsupervised 4D occupancy and flow (a, c) and can be decomposed into instance occupancy (b) as well as transfered to downstream tasks like LiDAR point cloud forecasting (d).
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext ea390796-c38c-4de0-b9b9-57f7b7b84a57Builds on23
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR SequencesJens Behley, Martin Garbade, Andres Milioto, Jan Quenzel et al.ICCV 2019 · 2,345 citations
- DenseTNT: End-to-end Trajectory Prediction from Dense Goal SetsJunru Gu, Chen Sun, Hang ZhaoICCV 2021 · 563 citations
- The Trajectron: Probabilistic Multi-Agent Trajectory Modeling With Dynamic Spatiotemporal GraphsBoris Ivanovic, Marco PavoneICCV 2019 · 473 citations
- Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene CompletionXu Yan, Jiantao Gao, Jie Li, Ruimao Zhang et al.AAAI 2021 · 365 citations
Related papers
- UnO: Unsupervised Occupancy Fields for Perception and ForecastingBen Agro, Quinlan Sykora, Sergio Casas, Thomas Gilles et al.CVPR 2024
- Occupancy Flow: 4D Reconstruction by Learning Particle DynamicsMichael Niemeyer, Lars M. Mescheder, Michael Oechsle, Andreas GeigerICCV 2019 · 314 citations
- Point Cloud Forecasting as a Proxy for 4D Occupancy ForecastingTarasha Khurana, Peiyun Hu, David Held, Deva RamananCVPR 2023
- -World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene ForecastingZhimin Liao, Ping Wei, Ruijie Zhang, Shuaijia Chen et al.ICCV 2025 · 1 citation
- Towards foundational LiDAR world models with efficient latent flow matchingTianran Liu, Shengwen Zhao, Nicholas RhinehartNeurIPS 2025 · 14 citations
