3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
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 ScanRe-fer and Nr3D/Sr3D datasets.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858826 · Cited by 9,556
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Zhou, Y., & Tuzel, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00472 · Cited by 4,813
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
Graham, B., Engelcke, M., & Maaten, L. V. D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00961 · Cited by 1,788
(2016) · doi:10.1007/978-3-319-46475-6_5 · Cited by 1,081
Cited by
Context-aware Alignment and Mutual Masking for 3D-Language Pre-training
Jin, Z., Hayat, M., Yang, Y., Guo, Y., & Lei, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01057 · Cited by 56
“We follow [6, 8, 11, 33] to evaluate grounding and captioning using “3D only” and “2D + 3D” inputs, where “3D only” means the input includes “xyz + normals + RGB” and “2D + 3D” means “xyz + normals + multiviews”, where “multiviews” are the 128-dim image features extracted as in [8].”
BackgroundMethodInfluentialTarget-Driven Structured Transformer Planner for Vision-Language Navigation
Zhao, Y., Chen, J., Gao, C., Wang, W., Yang, L., Ren, H., Xia, H., & Liu, S. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3548281 · Cited by 54
“A number of simulators [7, 29, 47] and datasets [11, 60] have been proposed, backing such tasks as navigation [4, 19], multi-agent cooperation [5, 41, 55], interactive learning [12], and visual grounding [1, 21, 37, 48].”
BackgroundSelf-citationViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding
Guo, Z., Tang, Y., Zhang, R., Wang, D., Wang, Z., Zhao, B., & Li, X. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01410 · Cited by 44
“Different from the two-stage methods, 3D-SPS [28] treats the 3D visual grounding task as a keypoint selection problem, and first proposes a single-stage network to bridge the gap between detection and matching.”
Method
Metadata
- Authors
- Luo, J., Fu, J., Kong, X., Gao, C., Ren, H., Shen, H., Xia, H., & Liu, S.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 16433-16442
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312749817
- Cited by
- 86
- References
- 6
- FWCI
- 6.76
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.