# Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding

arXiv: https://arxiv.org/abs/2410.15615 · HTML: https://mlsanity.com/paper/2410.15615/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 54 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [A Fast and Accurate One-Stage Approach to Visual Grounding](https://mlsanity.com/paper/1908.06354/) (2019)
- [Referring Transformer: A One-step Approach to Multi-task Visual Grounding](https://mlsanity.com/paper/2106.03089/) (2021)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [SAT: 2D Semantics Assisted Training for 3D Visual Grounding](https://mlsanity.com/paper/2105.11450/) (2021)
- [Learning Two-Branch Neural Networks for Image-Text Matching Tasks](https://mlsanity.com/paper/1704.03470/) (2017)
- [3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection](https://mlsanity.com/paper/2204.06272/) (2022)
- [Context-aware Biaffine Localizing Network for Temporal Sentence Grounding](https://mlsanity.com/paper/2103.11555/) (2021)
- [Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks](https://mlsanity.com/paper/1812.04794/) (2018)
- [TubeDETR: Spatio-Temporal Video Grounding with Transformers](https://mlsanity.com/paper/2203.16434/) (2022)
- [TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding](https://mlsanity.com/paper/2108.02388/) (2021)
- [A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends](https://mlsanity.com/paper/2407.07403/) (2024)
- [Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud](https://mlsanity.com/paper/2103.16381/) (2021)
- [Zero-Shot Grounding of Objects from Natural Language Queries](https://mlsanity.com/paper/1908.07129/) (2019)
- [Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization](https://mlsanity.com/paper/2008.01403/) (2020)

## Built on by (most cited first, 3 of 3)

- [Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras](https://mlsanity.com/paper/2507.17664/) (2025)
- [TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP](https://mlsanity.com/paper/2507.14904/) (2025)
- [Hard-Label Black-Box Attacks on 3D Point Clouds](https://mlsanity.com/paper/2412.00404/) (2024)

## Abstract (arXiv)

This paper tackles the challenging task of 3D visual grounding-locating a specific object in a 3D point cloud scene based on text descriptions. Existing methods fall into two categories: top-down and bottom-up methods. Top-down methods rely on a pre-trained 3D detector to generate and select the best bounding box, resulting in time-consuming processes. Bottom-up methods directly regress object bounding boxes with coarse-grained features, producing worse results. To combine their strengths while addressing their limitations, we propose a joint top-down and bottom-up framework, aiming to enhance the performance while improving the efficiency. Specifically, in the first stage, we propose a bottom-up based proposal generation module, which utilizes lightweight neural layers to efficiently regress and cluster several coarse object proposals instead of using a complex 3D detector. Then, in the second stage, we introduce a top-down based proposal consolidation module, which utilizes graph design to effectively aggregate and propagate the query-related object contexts among the generated proposals for further refinement. By jointly training these two modules, we can avoid the inherent drawbacks of the complex proposals in the top-down framework and the coarse proposals in the bottom-up framework. Experimental results on the ScanRefer benchmark show that our framework is able to achieve the state-of-the-art performance.