# SeqAlign3DVG: A Sequence-Aligned Benchmark and Voxel Reasoning Framework for 3D Visual Grounding

arXiv: https://arxiv.org/abs/2608.30451 · HTML: https://mlsanity.com/paper/2608.30451/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://mlsanity.com/paper/2211.09646/) (2022)
- [3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection](https://mlsanity.com/paper/2204.06272/) (2022)
- [TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding](https://mlsanity.com/paper/2108.02388/) (2021)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding](https://mlsanity.com/paper/2410.13860/) (2024)
- [MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations](https://mlsanity.com/paper/2406.09401/) (2024)
- [Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images](https://mlsanity.com/paper/2103.07894/) (2021)
- [ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenes](https://mlsanity.com/paper/2212.06250/) (2022)
- [NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving](https://mlsanity.com/paper/2503.22436/) (2025)
- [DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding](https://mlsanity.com/paper/2505.04965/) (2025)
- [BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence](https://mlsanity.com/paper/2411.14869/) (2024)
- [MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps](https://mlsanity.com/paper/2410.21566/) (2024)
- [ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding](https://mlsanity.com/paper/2501.01366/) (2025)
- [DEGround: An Effective Baseline for Ego-centric 3D Visual Grounding with a Homogeneous Framework](https://mlsanity.com/paper/2506.05199/) (2025)
- [Mono3DVG-EnSD: Enhanced Spatial-aware and Dimension-decoupled Text Encoding for Monocular 3D Visual Grounding](https://mlsanity.com/paper/2511.06908/) (2025)

## Abstract (arXiv)

Image-based 3D visual grounding is critical for embodied agents, yet existing benchmarks suffer from loose text-observation alignment and neglect temporal ordering. We introduce SeqAlign3DVG, a novel benchmark dedicated to temporally ordered and strictly observation-aligned image-based 3D visual grounding. Unlike prior works using order-agnostic views or global point clouds, SeqAlign3DVG ensures all expressions are human-verified and strictly grounded in the provided RGB observations (single frames or ordered observation sequences). It comprises 9,622 single-view and 14,493 sequence samples featuring rich descriptions, complex relations, and multi-instance ambiguities. To tackle this benchmark, we propose a unified voxel-based pipeline featuring Relevance-Ordered Voxel Memory (ROVM) and Progressive Language-Voxel Fusion (PLVF). ROVM dynamically ranks and aggregates multi-view evidence via a conservative memory to mitigate noisy observations, while PLVF performs coarse-to-fine spatial-linguistic reasoning for precise disambiguation. Our approach achieves state-of-the-art performance under the depth-free protocol, significantly improving localization for targets defined by complex relations and appearance cues.