InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring

• Published in: 2021 IEEE/CVF International Conference on Computer Vision (ICCV) pp. 1771 - 1780
• Main Authors: Yuan, Zhihao, Yan, Xu, Liao, Yinghong, Zhang, Ruimao, Wang, Sheng, Li, Zhen, Cui, Shuguang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2021
• Subjects: Detection and localization in 2D and 3D; Grounding; Location awareness; Point cloud compression; Predictive models; Scene analysis and understanding; Solid modeling; Three-dimensional displays; Vision + language; Visual reasoning and logical representation; Visualization
• ISSN: 2380-7504
• DOI: 10.1109/ICCV48922.2021.00181

Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer 1 , to achieve a superior 3D visual grounding through the grounding-by-matching strategy. In practice, our model first predicts the target category from the language descriptions using a simple language classification model. Then, based on the category, our model sifts out a small number of instance candidates (usually less than 20) from the panoptic segmentation on point clouds. Thus, the non-trivial 3D visual grounding task has been effectively re-formulated as a simplified instance-matching problem, considering that instance-level candidates are more rational than the redundant 3D object proposals. Subsequently, for each candidate, we perform the multi-level contextual inference, i.e., referring from instance attribute perception, instance-to-instance relation perception, and instance-to-background global localization perception, respectively. Eventually, the most relevant candidate is selected and localized by ranking confidence scores, which are obtained by the cooperative holistic visual-language feature matching. Experiments confirm that our method outperforms previous state-of-the-arts on ScanRefer online benchmark and Nr3D/Sr3D datasets.