OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
This work addresses the need for better visual grounding in cluttered robotic settings like offices and warehouses, but it is incremental as it primarily provides a new dataset rather than a novel method.
The authors tackled the problem of visual grounding for occluded objects in robotic environments by introducing the OCID-Ref dataset, which includes 305,694 referring expressions from 2,300 scenes with RGB and point cloud data, and found that combining 2D and 3D signals improves performance but occlusion remains a challenge for current systems.
To effectively apply robots in working environments and assist humans, it is essential to develop and evaluate how visual grounding (VG) can affect machine performance on occluded objects. However, current VG works are limited in working environments, such as offices and warehouses, where objects are usually occluded due to space utilization issues. In our work, we propose a novel OCID-Ref dataset featuring a referring expression segmentation task with referring expressions of occluded objects. OCID-Ref consists of 305,694 referring expressions from 2,300 scenes with providing RGB image and point cloud inputs. To resolve challenging occlusion issues, we argue that it's crucial to take advantage of both 2D and 3D signals to resolve challenging occlusion issues. Our experimental results demonstrate the effectiveness of aggregating 2D and 3D signals but referring to occluded objects still remains challenging for the modern visual grounding systems. OCID-Ref is publicly available at https://github.com/lluma/OCID-Ref