Related papers: SceneFactory: A Workflow-centric and Unified Frame…
Recent advancements in neural rendering technologies and their supporting devices have paved the way for immersive 3D experiences, significantly transforming human interaction with intelligent devices across diverse applications. However,…
Scene graphs are becoming a standard representation for robot navigation, providing hierarchical geometric and semantic scene understanding. However, most scene graph mapping methods rely on depth cameras or LiDAR sensors. In this work, we…
The choice of scene representation is crucial in both the shape inference algorithms it requires and the smart applications it enables. We present efficient and optimisable multi-class learned object descriptors together with a novel…
As the landscape of deep neural networks evolves, heterogeneous dataflow accelerators, in the form of multi-core architectures or chiplet-based designs, promise more flexibility and higher inference performance through scalability. So far,…
In recent years, neural implicit surface reconstruction has emerged as a popular paradigm for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods leverage neural networks…
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…
Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models often struggle with this relational understanding,…
Grounding complex, compositional visual queries with multiple objects and relationships is a fundamental challenge for vision-language models. While standard phrase grounding methods excel at localizing single objects, they lack the…
RGB-D tracking significantly improves the accuracy of object tracking. However, its dependency on real depth inputs and the complexity involved in multi-modal fusion limit its applicability across various scenarios. The utilization of depth…
In this work, we introduce StageDesigner, the first comprehensive framework for artistic stage generation using large language models combined with layout-controlled diffusion models. Given the professional requirements of stage…
Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps…
Careful robot manipulation in every-day cluttered environments requires an accurate understanding of the 3D scene, in order to grasp and place objects stably and reliably and to avoid colliding with other objects. In general, we must…
Detecting what has changed in an environment is essential for long-term autonomy, yet most change detection settings assume fixed viewpoints, mild misalignment, or only a few changed objects. We introduce Video-based Scene Change Detection…
Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…
Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged…
Monocular Indoor Semantic Scene Completion (SSC) aims to reconstruct a 3D semantic occupancy map from a single RGB image of an indoor scene, inferring spatial layout and object categories from 2D image cues. The challenge of this task…
Indoor scenes exhibit significant appearance variations due to myriad interactions between arbitrarily diverse object shapes, spatially-changing materials, and complex lighting. Shadows, highlights, and inter-reflections caused by visible…
Generative models have gained significant attention in novel view synthesis (NVS) by alleviating the reliance on dense multi-view captures. However, existing methods typically fall into a conventional paradigm, where generative models first…
We introduce the task of predicting functional 3D scene graphs for real-world indoor environments from posed RGB-D images. Unlike traditional 3D scene graphs that focus on spatial relationships of objects, functional 3D scene graphs capture…
Visual simultaneous localization and mapping (SLAM) plays a critical role in autonomous robotic systems, especially where accurate and reliable measurements are essential for navigation and sensing. In feature-based SLAM, the quantityand…