Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D …
Although great progress has been made in 3D visual grounding, current models still rely on explicit textual descriptions for grounding and lack the ability to reason human intentions …
As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and …
With the emergence of LLMs and their integration with other data modalities, multi-modal 3D perception attracts more attention due to its connectivity to the physical world and makes …
The integration of language and 3D perception is crucial for developing embodied agents and robots that comprehend and interact with the physical world. While large language …
Z Wang, Z Zhang, H Zhang, L Liu, R Huang… - arXiv preprint arXiv …, 2024 - arxiv.org
Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Given the foundational role of multimodal joint …
S Linok, T Zemskova, S Ladanova, R Titkov… - arXiv preprint arXiv …, 2024 - arxiv.org
Locating objects referred to in natural language poses a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform …
In real-life scenarios, humans seek out objects in the 3D world to fulfill their daily needs or intentions. This inspires us to introduce 3D intention grounding, a new task in 3D object …
Unified multi-model representation spaces are the foundation of multimodal understanding and generation. However, the billions of model parameters and catastrophic forgetting …