4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer

TL;DR

This paper introduces 4DLangVGGT, a Transformer-based framework for 4D language grounding that effectively models dynamic scenes and generalizes across multiple scenes, outperforming prior scene-specific methods.

Contribution

The paper presents the first unified Transformer-based approach for 4D language grounding that jointly models geometry and semantics, enabling scalable and generalizable 4D scene understanding.

Findings

Achieves state-of-the-art results on HyperNeRF and Neu3D datasets.

Demonstrates effective generalization across multiple dynamic scenes.

Outperforms scene-specific methods with up to 2% accuracy gains.

Abstract

Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic environments and enable open-vocabulary querying in complex scenarios. However, existing approaches to 4D semantic field construction primarily rely on scene-specific Gaussian splatting, which requires per-scene optimization, exhibits limited generalization, and is difficult to scale to real-world applications. To address these limitations, we propose 4DLangVGGT, the first Transformer-based feed-forward unified framework for 4D language grounding, that jointly integrates geometric perception and language alignment within a single architecture. 4DLangVGGT has two key components: the 4D Visual Geometry Transformer, StreamVGGT, which captures spatio-temporal geometric representations of dynamic scenes; and the Semantic Bridging Decoder (SBD), which projects geometry-aware features into a language-aligned semantic space, thereby enhancing semantic interpretability while preserving structural fidelity. Unlike prior methods that depend on costly per-scene optimization, 4DLangVGGT can be jointly trained across multiple dynamic scenes and directly applied during inference, achieving both deployment efficiency and strong generalization. This design significantly improves the practicality of large-scale deployment and establishes a new paradigm for open-vocabulary 4D scene understanding. Experiments on HyperNeRF and Neu3D datasets demonstrate that our approach not only generalizes effectively but also achieves state-of-the-art performance, achieving up to 2% gains under per-scene training and 1% improvements under multi-scene training. Our code released in https://github.com/hustvl/4DLangVGGT