Related papers: Distill, Diffuse, and Semanticize (DDS): Annotatio…

Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the…

Scene understanding has been of high interest in computer vision. It encompasses not only identifying objects in a scene, but also their relationships within the given context. With this goal, a recent line of works tackles 3D semantic…

Semantic segmentation of 3D point clouds is a challenging problem with numerous real-world applications. While deep learning has revolutionized the field of image semantic segmentation, its impact on point cloud data has been limited so…

The open vocabulary capability of 3D models is increasingly valued, as traditional methods with models trained with fixed categories fail to recognize unseen objects in complex dynamic 3D scenes. In this paper, we propose a simple yet…

Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work, we jointly address…

We propose a novel framework to learn 3D point cloud semantics from 2D multi-view image observations containing pose error. On the one hand, directly learning from the massive, unstructured and unordered 3D point cloud is computationally…

3D panoptic segmentation is a challenging perception task, especially in autonomous driving. It aims to predict both semantic and instance annotations for 3D points in a scene. Although prior 3D panoptic segmentation approaches have…

Few-shot semantic segmentation (FSS) offers immense potential in the field of medical image analysis, enabling accurate object segmentation with limited training data. However, existing FSS techniques heavily rely on annotated semantic…

As 3D perception problems grow in popularity and the need for large-scale labeled datasets for LiDAR semantic segmentation increase, new methods arise that aim to reduce the necessity for dense annotations by employing weakly-supervised…

End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small…

The deficiency of 3D segmentation labels is one of the main obstacles to effective point cloud segmentation, especially for scenes in the wild with varieties of different objects. To alleviate this issue, we propose a novel deep graph…

Recent research on deep convolutional neural networks (CNNs) has provided a significant performance boost on efficient super-resolution (SR) tasks by trading off the performance and applicability. However, most existing methods focus on…

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…

Current deep learning-based approaches for the segmentation of microscopy images heavily rely on large amount of training data with dense annotation, which is highly costly and laborious in practice. Compared to full annotation where the…

As three-dimensional (3D) data acquisition devices become increasingly prevalent, the demand for 3D point cloud transmission is growing. In this study, we introduce a semantic-aware communication system for robust point cloud classification…

3D Multi-modal Large Language Models (MLLMs) still lag behind their 2D peers, largely because large-scale, high-quality 3D scene-dialogue datasets remain scarce. Prior efforts hinge on expensive human annotation and leave two key…

Semantic understanding of 3D scenes is essential for robots to operate effectively and safely in complex environments. Existing methods for semantic scene reconstruction and semantic-aware novel view synthesis often rely on dense multi-view…

Dataset distillation, a training-aware data compression technique, has recently attracted increasing attention as an effective tool for mitigating costs of optimization and data storage. However, progress remains largely empirical.…

Semantic segmentation of raw 3D point clouds is an essential component in 3D scene analysis, but it poses several challenges, primarily due to the non-Euclidean nature of 3D point clouds. Although, several deep learning based approaches…

Vision-based perception and reasoning is essential for scene understanding in any autonomous system. RGB and depth images are commonly used to capture both the semantic and geometric features of the environment. Developing methods to…