Related papers: GroundFlow: A Plug-in Module for Temporal Reasonin…
We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as point clouds, spectral…
As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ…
Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary…
3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, grounding language in…
3D semantic segmentation on multi-scan large-scale point clouds plays an important role in autonomous systems. Unlike the single-scan-based semantic segmentation task, this task requires distinguishing the motion states of points in…
Vision-language models (VLMs) have achieved strong performance in multimodal understanding and reasoning, yet grounded reasoning in 3D scenes remains underexplored. Effective 3D reasoning hinges on accurate grounding: to answer open-ended…
Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant…
Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few…
Temporal Action Detection and Moment Retrieval constitute two pivotal tasks in video understanding, focusing on precisely localizing temporal segments corresponding to specific actions or events. Recent advancements introduced Moment…
This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expensive in computation and storage, and depend on time-consuming…
Video grounding aims to localize the corresponding video moment in an untrimmed video given a language query. Existing methods often address this task in an indirect way, by casting it as a proposal-and-match or fusion-and-detection…
3D visual grounding aims at grounding a natural language description about a 3D scene, usually represented in the form of 3D point clouds, to the targeted object region. Point clouds are sparse, noisy, and contain limited semantic…
3D scene understanding spans reasoning about free space, object grounding, hypothetical object insertions, complex geometric relationships, and integrating all of these with external tools and data sources. Existing 3D understanding methods…
Understanding and localizing objects in complex 3D environments from natural language descriptions, known as 3D Visual Grounding (3DVG), is a foundational challenge in embodied AI, with broad implications for robotics, augmented reality,…
Generating realistic 3D point clouds is a fundamental problem in computer vision with applications in remote sensing, robotics, and digital object modeling. Existing generative approaches primarily capture geometry, and when semantics are…
The advancement of 3D language fields has enabled intuitive interactions with 3D scenes via natural language. However, existing approaches are typically limited to small-scale environments, lacking the scalability and compositional…
3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive…
Point cloud registration aligns multiple unposed point clouds into a common reference frame and is a core step for 3D reconstruction and robot localization without initial guess. In this work, we cast registration as conditional generation:…
Reasoning is a fundamental substrate for solving novel and complex problems. Deliberate efforts in learning and developing frameworks around System 2 reasoning have made great strides, yet problems of sufficient complexity remain largely…