D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding
This work addresses challenges in 3D vision-language tasks for applications like robotics and augmented reality, but it is incremental as it builds on existing methods.
The paper tackles the problem of overfitting and discriminative description in 3D dense captioning and visual grounding due to limited data, presenting D3Net, which unifies these tasks and outperforms state-of-the-art methods on the ScanRefer dataset.
Recent studies on dense captioning and visual grounding in 3D have achieved impressive results. Despite developments in both areas, the limited amount of available 3D vision-language data causes overfitting issues for 3D visual grounding and 3D dense captioning methods. Also, how to discriminatively describe objects in complex 3D environments is not fully studied yet. To address these challenges, we present D3Net, an end-to-end neural speaker-listener architecture that can detect, describe and discriminate. Our D3Net unifies dense captioning and visual grounding in 3D in a self-critical manner. This self-critical property of D3Net also introduces discriminability during object caption generation and enables semi-supervised training on ScanNet data with partially annotated descriptions. Our method outperforms SOTA methods in both tasks on the ScanRefer dataset, surpassing the SOTA 3D dense captioning method by a significant margin.