3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
About
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description. Previous methods mostly follow a two-stage paradigm, i.e., language-irrelevant detection and cross-modal matching, which is limited by the isolated architecture. In such a paradigm, the detector needs to sample keypoints from raw point clouds due to the inherent properties of 3D point clouds (irregular and large-scale), to generate the corresponding object proposal for each keypoint. However, sparse proposals may leave out the target in detection, while dense proposals may confuse the matching model. Moreover, the language-irrelevant detection stage can only sample a small proportion of keypoints on the target, deteriorating the target prediction. In this paper, we propose a 3D Single-Stage Referred Point Progressive Selection (3D-SPS) method, which progressively selects keypoints with the guidance of language and directly locates the target. Specifically, we propose a Description-aware Keypoint Sampling (DKS) module to coarsely focus on the points of language-relevant objects, which are significant clues for grounding. Besides, we devise a Target-oriented Progressive Mining (TPM) module to finely concentrate on the points of the target, which is enabled by progressive intra-modal relation modeling and inter-modal target mining. 3D-SPS bridges the gap between detection and matching in the 3D visual grounding task, localizing the target at a single stage. Experiments demonstrate that 3D-SPS achieves state-of-the-art performance on both ScanRefer and Nr3D/Sr3D datasets.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3D Visual Grounding | ScanRefer (val) | Overall Accuracy @ IoU 0.5037 | 155 | |
| 3D Visual Grounding | Nr3D (test) | Overall Success Rate51.5 | 88 | |
| 3D Visual Grounding | Nr3D | Overall Success Rate51.5 | 74 | |
| 3D Visual Grounding | Sr3D (test) | Overall Accuracy62.6 | 73 | |
| 3D Visual Grounding | ScanRefer | -- | 23 | |
| 3D Point Cloud Affordance Prediction | LASO-C 1.0 (Seen) | aIoU11.4 | 21 | |
| 3D Visual Grounding | ScanRefer (test) | -- | 21 | |
| 3D Object Grounding | ScanRefer detected proposals v1 (val) | Unique Acc@0.2581.63 | 10 | |
| 3D Visual Grounding | Sr3D | Overall Accuracy62.6 | 7 | |
| 3D Affordance Learning | LASO (Unseen) | aIoU0.079 | 7 |