Related papers: RegionPLC: Regional Point-Language Contrastive Lea…
Understanding scene contexts is crucial for machines to perform tasks and adapt prior knowledge in unseen or noisy 3D environments. As data-driven learning is intractable to comprehensively encapsulate diverse ranges of layouts and open…
Enabling agents to understand and interact with complex 3D scenes is a fundamental challenge for embodied artificial intelligence systems. While Multimodal Large Language Models (MLLMs) have achieved significant progress in 2D image…
Open-vocabulary 3D scene understanding is crucial for applications requiring natural language-driven spatial interpretation, such as robotics and augmented reality. While 3D Gaussian Splatting (3DGS) offers a powerful representation for…
Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs, yet they struggle with detailed regional visual understanding due to limited spatial awareness…
In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…
Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional…
Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information…
Recent advances in 3D reconstruction techniques and vision-language models have fueled significant progress in 3D semantic understanding, a capability critical to robotics, autonomous driving, and virtual/augmented reality. However, methods…
3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction, offering high-quality novel view synthesis while maintaining computational efficiency. In this paper, we extend the capabilities of 3DGS…
LiDAR-based 3D object detection has recently seen significant advancements through active learning (AL), attaining satisfactory performance by training on a small fraction of strategically selected point clouds. However, in real-world…
Research on 3D Vision-Language Models (3D-VLMs) is gaining increasing attention, which is crucial for developing embodied AI within 3D scenes, such as visual navigation and embodied question answering. Due to the high density of visual…
Detecting objects accurately from a large or open vocabulary necessitates the vision-language alignment on region representations. However, learning such a region-text alignment by obtaining high-quality box annotations with text labels or…
Recently, methods have been proposed for 3D open-vocabulary semantic segmentation. Such methods are able to segment scenes into arbitrary classes based on text descriptions provided during runtime. In this paper, we propose to the best of…
Holistic 3D scene understanding, which jointly models geometry, appearance, and semantics, is crucial for applications like augmented reality and robotic interaction. Existing feed-forward 3D scene understanding methods (e.g., LSM) are…
In this paper, we introduce MultiviewVLM, a vision-language model designed for unsupervised contrastive multiview representation learning of facial emotions from 3D/4D data. Our architecture integrates pseudo-labels derived from generated…
Despite encouraging progress in 3D scene understanding, it remains challenging to develop an effective Large Multi-modal Model (LMM) that is capable of understanding and reasoning in complex 3D environments. Most previous methods typically…
New era has unlocked exciting possibilities for extending Large Language Models (LLMs) to tackle 3D vision-language tasks. However, most existing 3D multimodal LLMs (MLLMs) rely on compressing holistic 3D scene information or segmenting…
Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning. Compared to standard object detection, the OWOD setting is task to: 1) detect objects seen during…
Recent advancements in multi-modal large language models (MLLMs) have shown strong potential for 3D scene understanding. However, existing methods struggle with fine-grained object grounding and contextual reasoning, limiting their ability…
The presence of occlusions has provided substantial challenges to typically-powerful object recognition algorithms. Additional sources of information can be extremely valuable to reduce errors caused by occlusions. Scene context is known to…