A Unified Framework for 3D Scene Understanding
This work addresses the need for comprehensive 3D scene understanding in fields like robotics and autonomous driving by unifying multiple segmentation tasks, though it is incremental in building on existing Transformer-based methods.
The paper tackles the problem of fragmented 3D scene understanding by proposing UniSeg3D, a unified framework that handles six segmentation tasks within a single model, and it demonstrates superior performance over specialized state-of-the-art methods on benchmarks like ScanNet20, ScanRefer, and ScanNet200.
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are typically tailored to a specific task, limiting their understanding of 3D scenes to a task-specific perspective. In contrast, the proposed method unifies six tasks into unified representations processed by the same Transformer. It facilitates inter-task knowledge sharing, thereby promoting comprehensive 3D scene understanding. To take advantage of multi-task unification, we enhance performance by establishing explicit inter-task associations. Specifically, we design knowledge distillation and contrastive learning methods to transfer task-specific knowledge across different tasks. Experiments on three benchmarks, including ScanNet20, ScanRefer, and ScanNet200, demonstrate that the UniSeg3D consistently outperforms current SOTA methods, even those specialized for individual tasks. We hope UniSeg3D can serve as a solid unified baseline and inspire future work. Code and models are available at https://github.com/dk-liang/UniSeg3D.