Related papers: PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal…
3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the…
We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images and 3D LiDAR point clouds. We present a novel method,…
Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption…
Visual grounding tasks, such as referring image segmentation (RIS) and referring expression comprehension (REC), aim to localize a target object based on a given textual description. The target object in an image can be described in…
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent UDA methods based on Vision Transformers (ViTs) have achieved strong performance through attention-based…
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,…
Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works…
Referring segmentation aims to segment a target object related to a natural language expression. Key challenges of this task are understanding the meaning of complex and ambiguous language expressions and determining the relevant regions in…
Referring Expression Comprehension (REC) is a popular multimodal task that aims to accurately detect target objects within a single image based on a given textual expression. However, due to the limitations of earlier models, traditional…
3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment…
Existing 3D visual grounding methods rely on precise text prompts to locate objects within 3D scenes. Speech, as a natural and intuitive modality, offers a promising alternative. Real-world speech inputs, however, often suffer from…
3D visual grounding aims to identify the target object within a 3D point cloud scene referred to by a natural language description. Previous works usually require significant data relating to point color and their descriptions to exploit…
Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually…
State-of-the-art 3D models, which excel in recognition tasks, typically depend on large-scale datasets and well-defined category sets. Recent advances in multi-modal pre-training have demonstrated potential in learning 3D representations by…
We propose a lightweight and scalable Regional Point-Language Contrastive learning framework, namely \textbf{RegionPLC}, for open-world 3D scene understanding, aiming to identify and recognize open-set objects and categories. Specifically,…
Current 3D visual grounding tasks only process sentence level detection or segmentation, which critically fails to leverage the rich compositional contextual reasonings within natural language expressions. To address this challenge, we…
This paper tackles the challenging task of 3D visual grounding-locating a specific object in a 3D point cloud scene based on text descriptions. Existing methods fall into two categories: top-down and bottom-up methods. Top-down methods rely…
To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point…
3D Referring Expression Segmentation (3D-RES) aims to segment point cloud scenes based on a given expression. However, existing 3D-RES approaches face two major challenges: feature ambiguity and intent ambiguity. Feature ambiguity arises…
The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…