Related papers: Bridging the Domain Gap: Self-Supervised 3D Scene …

D scene graphs are an emerging 3D scene representation, that models both the objects present in the scene as well as their relationships. However, learning 3D scene graphs is a challenging task because it requires not only object labels but…

This work investigates descriptive captions as an additional source of supervision for biological multimodal foundation models. Images and captions can be viewed as complementary samples from the latent morphospace of a species, each…

Closed-set 3D perception models trained on only a pre-defined set of object categories can be inadequate for safety critical applications such as autonomous driving where new object types can be encountered after deployment. In this paper,…

Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have emerged tackling this problem in an unsupervised fashion.…

Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on…

Large unimodal foundation models for vision and language encode rich semantic structures, yet aligning them typically requires computationally intensive multimodal fine-tuning. Such approaches depend on large-scale parameter updates, are…

Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent works have sought to transfer knowledge embedded in vision-language models from 2D to 3D domains. However, these approaches often require prior…

Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise…

Learning descriptive 3D features is crucial for understanding 3D scenes with diverse objects and complex structures. However, it is usually unknown whether important geometric attributes and scene context obtain enough emphasis in an…

Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution. To reduce such domain gaps and thus to make 3DOD…

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…

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes…

Current unsupervised domain adaptation (UDA) methods for semantic segmentation typically assume identical class labels between the source and target domains. This assumption ignores the label-level domain gap, which is common in real-world…

As a fundamental task in computer vision, semantic segmentation is widely applied in fields such as autonomous driving, remote sensing image analysis, and medical image processing. In recent years, Transformer-based segmentation methods…

Connecting current observations with prior experiences helps robots adapt and plan in new, unseen 3D environments. Recently, 3D scene analogies have been proposed to connect two 3D scenes, which are smooth maps that align scene regions with…

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…

Industrial anomaly detection for 2D objects has gained significant attention and achieved progress in anomaly detection (AD) methods. However, identifying 3D depth anomalies using only 2D information is insufficient. Despite explicitly…

In embodied intelligence systems, a key component is 3D perception algorithm, which enables agents to understand their surrounding environments. Previous algorithms primarily rely on point cloud, which, despite offering precise geometric…

Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they…

Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR). To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques…