InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting

• URL: http://arxiv.org/abs/2607.24431v1
• Date: Mon, 27 Jul 2026 13:43:37 GMT
• Title: InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting
• Abstract summary: Camera-only 4D occupancy forecasting enables autonomous vehicles to predict future 3D semantic scenes solely from historical multi-view images.<n>We introduce a novel framework, InterOCF, for 4D occupancy forecasting that jointly models temporal dynamics in both 3D voxel-based representations and multi-view segmentation sequences.<n>Our framework incorporates three core components: 1) A 3D Spatio-Temporal (3DST) module that learns volumetric dynamics from historical voxel states to predict future voxel states; 2) A 2D Spatio-Temporal (2DST) module employing an auxiliary multi-view temporal segmentation forecasting
• Score: 14.13719947869133
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Camera-only 4D occupancy forecasting enables autonomous vehicles to predict future 3D semantic scenes solely from historical multi-view images, which is critical for driving safety. Even though current methods have achieved good performance, the strong spatial-temporal modeling between the input multi-view frames is still underexplored, which limits the performance of those methods in future 4D forecasting. To address this gap, we introduce a novel framework, InterOCF, for 4D occupancy forecasting that jointly models temporal dynamics in both 3D voxel-based representations and multi-view segmentation sequences, while explicitly incorporating feature interaction between the 2D and 3D branches. Our framework incorporates three core components: 1) A 3D Spatio-Temporal (3DST) module that learns volumetric dynamics from historical voxel states to predict future voxel states; 2) A 2D Spatio-Temporal (2DST) module employing an auxiliary multi-view temporal segmentation forecasting task to enhance temporal semantic dynamics; 3) A Spatio-Temporal Interaction Modeling (STIM) module that enables feature interaction between 2D and 3D representations. Experiments on the nuScenes, Lyft-Level5, and nuScenes-Occupancy datasets show that InterOCF consistently outperforms existing baseline approaches.

Related papers

• From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video [62.898774619819676]
  Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize them.<n>We introduce Coherent4D, a large-scale egocentric dataset for continuous 4D interaction forecasting, comprising approximately 233K samples across three domains.<n>We propose HIGFlow, a Hand Interaction Guided Residual Flow framework that models forecasting as a cascaded where-to-how process.
  arXiv  Detail & Related papers  (2026-09-08T12:06:23Z)
• Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecasting [45.44434144383036]
  We propose a Geometry-Aware Spatio-Temporal context modeling method (GAST) for 4D occupancy forecasting.<n> Specifically, the generation module produces per-frame occupancy with high geometric fidelity and semantic plausibility.<n>Experiments on Occ3D-nus demonstrate the superiority of our method, outperforming the state-of-the-art by 7.67% in mIoU and 6.44% in IoU with a 2.84x speedup.
  arXiv  Detail & Related papers  (2026-08-15T15:22:29Z)
• 4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields [35.51443781145251]
  World Action Models (WAMs) jointly model video prediction and action generation.<n>WAMs typically represent videos in 2D pixel space, creating a representation gap with 3D space in which robotic actions are executed.<n>Recent 3D approaches introduce 3D information, but fail to fully exploit the dynamics of 3D structures.<n>We propose 4D-WAM, a model-agnostic training strategy that injects knowledge from 3D trajectory fields into WAMs through alignment.
  arXiv  Detail & Related papers  (2026-08-08T09:11:05Z)
• StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation [6.0744834626758495]
  StemVLA is a novel framework that explicitly incorporates both future-oriented 3D spatial knowledge and historical 4D representations into action prediction.<n>We show that StemVLA significantly improves long-horizon task success and state-of-the-art performance on the CALVIN ABC-D benchmark [46], achieving an average sequence length of XXX.
  arXiv  Detail & Related papers  (2026-02-27T06:43:37Z)
• SS4D: Native 4D Generative Model via Structured Spacetime Latents [50.29500511908054]
  We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video.<n>We train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency.
  arXiv  Detail & Related papers  (2025-12-16T10:45:06Z)
• Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding [54.859943475818234]
  We present Motion4D, a novel framework that integrates 2D priors from foundation models into a unified 4D Gaussian Splatting representation.<n>Our method features a two-part iterative optimization framework: 1) Sequential optimization, which updates motion and semantic fields in consecutive stages to maintain local consistency, and 2) Global optimization, which jointly refines all attributes for long-term coherence.<n>Our method significantly outperforms both 2D foundation models and existing 3D-based approaches across diverse scene understanding tasks, including point-based tracking, video object segmentation, and novel view synthesis.
  arXiv  Detail & Related papers  (2025-12-03T09:32:56Z)
• Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perception [9.76463525667238]
  We propose Doracamom, the first framework that fuses multi-view cameras and 4D radar for joint 3D object detection and semantic occupancy prediction.<n>Code and models will be publicly available.
  arXiv  Detail & Related papers  (2025-01-26T04:24:07Z)
• Modeling Continuous Motion for 3D Point Cloud Object Tracking [54.48716096286417]
  This paper presents a novel approach that views each tracklet as a continuous stream. At each timestamp, only the current frame is fed into the network to interact with multi-frame historical features stored in a memory bank. To enhance the utilization of multi-frame features for robust tracking, a contrastive sequence enhancement strategy is proposed.
  arXiv  Detail & Related papers  (2023-03-14T02:58:27Z)
• DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention [50.11672196146829]
  3D object detection with surround-view images is an essential task for autonomous driving. We propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in multi-view images.
  arXiv  Detail & Related papers  (2022-12-15T14:18:47Z)
• Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes [82.4186966781934]
  We introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules. With negligible extra overhead, Ret3D achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-08-18T03:48:58Z)
• Learning Spatial and Temporal Variations for 4D Point Cloud Segmentation [0.39373541926236766]
  We argue that the temporal information across the frames provides crucial knowledge for 3D scene perceptions. We design a temporal variation-aware module and a temporal voxel-point refiner to capture the temporal variation in the 4D point cloud.
  arXiv  Detail & Related papers  (2022-07-11T07:36:26Z)
• Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding [61.57847727651068]
  Temporal sentence grounding aims to localize a target segment in an untrimmed video semantically according to a given sentence query. Most previous works focus on learning frame-level features of each whole frame in the entire video, and directly match them with the textual information. We propose a novel Motion- and Appearance-guided 3D Semantic Reasoning Network (MA3SRN), which incorporates optical-flow-guided motion-aware, detection-based appearance-aware, and 3D-aware object-level features.
  arXiv  Detail & Related papers  (2022-03-06T13:57:09Z)
• Spatio-Temporal Self-Attention Network for Video Saliency Prediction [13.873682190242365]
  3D convolutional neural networks have achieved promising results for video tasks in computer vision. We propose a novel Spatio-Temporal Self-Temporal Self-Attention 3 Network (STSANet) for video saliency prediction.
  arXiv  Detail & Related papers  (2021-08-24T12:52:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.