4D Panoptic Scene Graph Generation

TL;DR

This paper introduces PSG-4D, a novel 4D scene graph representation for dynamic environments, along with a new dataset and a Transformer-based model, enabling comprehensive understanding of 4D scenes for AI applications.

Contribution

We propose PSG-4D, a new 4D scene graph representation, a large annotated dataset, and a Transformer-based model for dynamic scene understanding in 4D environments.

Findings

PSG4DFormer effectively predicts 4D panoptic segmentation and scene graphs.

The dataset contains 3K RGB-D videos with 1M frames labeled with 4D masks.

Our method establishes a strong baseline for future 4D scene graph research.

Abstract

We are living in a three-dimensional space while moving forward through a fourth dimension: time. To allow artificial intelligence to develop a comprehensive understanding of such a 4D environment, we introduce 4D Panoptic Scene Graph (PSG-4D), a new representation that bridges the raw visual data perceived in a dynamic 4D world and high-level visual understanding. Specifically, PSG-4D abstracts rich 4D sensory data into nodes, which represent entities with precise location and status information, and edges, which capture the temporal relations. To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as fine-grained, dynamic scene graphs. To solve PSG-4D, we propose PSG4DFormer, a Transformer-based model that can predict panoptic segmentation masks, track masks along the time axis, and generate the corresponding scene graphs via a relation component. Extensive experiments on the new dataset show that our method can serve as a strong baseline for future research on PSG-4D. In the end, we provide a real-world application example to demonstrate how we can achieve dynamic scene understanding by integrating a large language model into our PSG-4D system.