Related papers: OpenDlign: Open-World Point Cloud Understanding wi…

Understanding 3D medical image volumes is a critical task in the medical domain. However, existing 3D convolution and transformer-based methods have limited semantic understanding of an image volume and also need a large set of volumes for…

3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate…

Large-scale datasets are usually required to train deep neural networks, but it increases the computational complexity hindering the practical applications. Recently, dataset distillation for images and texts has been attracting a lot of…

Vision-Language-Action (VLA) models excel at robotic tasks by leveraging large-scale 2D vision-language pretraining, but their reliance on RGB images limits spatial reasoning critical for real-world interaction. Retraining these models with…

Advancements in foundation models have made it possible to conduct applications in various downstream tasks. Especially, the new era has witnessed a remarkable capability to extend Large Language Models (LLMs) for tackling tasks of 3D scene…

Recent studies that incorporate geometric features and transformers into 3D point cloud feature learning have significantly improved the performance of 3D deep-learning models. However, their robustness against adversarial attacks has not…

Recent open-world representation learning approaches have leveraged CLIP to enable zero-shot 3D object recognition. However, performance on real point clouds with occlusions still falls short due to unrealistic pretraining settings.…

This paper presents a novel 3D semantic segmentation method for large-scale point cloud data that does not require annotated 3D training data or paired RGB images. The proposed approach projects 3D point clouds onto 2D images using virtual…

Recently,vision-based robotic manipulation has garnered significant attention and witnessed substantial advancements. 2D image-based and 3D point cloud-based policy learning represent two predominant paradigms in the field, with recent…

3D visual grounding (3DVG) identifies objects in 3D scenes from language descriptions. Existing zero-shot approaches leverage 2D vision-language models (VLMs) by converting 3D spatial information (SI) into forms amenable to VLM processing,…

Point-cloud data collected in real-world applications are often incomplete. Data is typically missing due to objects being observed from partial viewpoints, which only capture a specific perspective or angle. Additionally, data can be…

Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural language processing, this work proposes a novel Multi-view…

Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, i.e., aligning point cloud representation to image and text embedding space individually. In this paper, we introduce MixCon3D, a simple yet effective…

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions,…

Recently, large-scale pre-trained models such as Segment-Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP) have demonstrated remarkable success and revolutionized the field of computer vision. These foundation vision…

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (e.g., CLIP) with a tremendous amount of image-text pair data, has shown its superiority on various multimodal alignment tasks. Despite its success, the…

3D part assembly aims to understand part relationships and predict their 6-DoF poses to construct realistic 3D shapes, addressing the growing demand for autonomous assembly, which is crucial for robots. Existing methods mainly estimate the…

Orthodontic treatment hinges on tooth alignment, which significantly affects occlusal function, facial aesthetics, and patients' quality of life. Current deep learning approaches predominantly concentrate on predicting transformation…

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which…

Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their tendency to make biased predictions, often favoring the classes…