Overview

4D scene understanding uses video and multi-view observations to recover scene geometry, track persistent objects, and interpret their motion and interactions. Common approaches include dynamic NeRFs and Gaussian splatting, point-cloud and occupancy models, scene graphs, and vision-language models that connect visual evidence with queries or actions. These methods support tasks such as novel-view rendering, occupancy forecasting, dynamic grounding, and robot planning, with evaluations on settings including nuScenes, Waymo, and HyperNeRF. A central challenge is balancing detailed, temporally consistent representations with efficient inference and reliable generalization, especially when observations are incomplete or language models must ground their answers in 3D motion.

Latest papers

CardsList

64 papers9 papers in the last four weeks, down 44% on the four weeks before. 0.1% of all new papers.

  1. MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence

    Feb 28, 2026Xingyilang Yin, Chengzhengxu Li, Jiahao Chang +2Spatiotemporal ReasoningMultimodal Large Language Models

  2. Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

    Feb 26, 2026Maximilian Luz, Rohit Mohan, Thomas Nürnberg +34D Scene Understanding3D Occupancy Prediction

  3. Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception

    Feb 26, 2026Yiding Sun, Jihua Zhu, Haozhe Cheng +4Transfer LearningPoint Cloud Learning

  4. Stereo4DWalker: Learning 4D-aware Embodied Urban Navigation from Internet Stereo Videos

    Dec 11, 2025Wentao Zhou, Xuweiyi Chen, Vignesh Rajagopal +3Embodied NavigationRobot Navigation