Related papers: TabletopGen: Instance-Level Interactive 3D Tableto…

Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capability, termed compositional 3D reconstruction, is pivotal…

Controllable scene synthesis consists of generating 3D information that satisfy underlying specifications. Thereby, these specifications should be abstract, i.e. allowing easy user interaction, whilst providing enough interface for detailed…

Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation. Although recent methods achieve high-fidelity reconstructions, they either rely on costly human annotations for object…

Prompt-driven scene synthesis allows users to generate complete 3D environments from textual descriptions. Current text-to-scene methods often struggle with complex geometries and object transformations, and tend to show weak adherence to…

We present a dataset of 998 3D models of everyday tabletop objects along with their 847,000 real world RGB and depth images. Accurate annotations of camera poses and object poses for each image are performed in a semi-automated fashion to…

City scene generation has gained significant attention in autonomous driving, smart city development, and traffic simulation. It helps enhance infrastructure planning and monitoring solutions. Existing methods have employed a two-stage…

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…

The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures…

Accurately reconstructing complex full multi-object scenes from sparse observations remains a core challenge in computer vision and a key step toward scalable and reliable simulation for robotics. In this work, we introduce RecGen, a…

Manipulation policies deployed in uncontrolled real-world scenarios are faced with great in-category geometric diversity of everyday objects. In order to function robustly under such variations, policies need to work in a category-level…

How can one efficiently generate high-quality, wide-scope 3D scenes from arbitrary single images? Existing methods suffer several drawbacks, such as requiring multi-view data, time-consuming per-scene optimization, distorted geometry in…

Generating artistic and coherent 3D scene layouts is crucial in digital content creation. Traditional optimization-based methods are often constrained by cumbersome manual rules, while deep generative models face challenges in producing…

In this paper, we present a new text-guided 3D shape generation approach DreamStone that uses images as a stepping stone to bridge the gap between text and shape modalities for generating 3D shapes without requiring paired text and 3D data.…

Scene generation has extensive industrial applications, demanding both high realism and precise control over geometry and appearance. Language-driven retrieval methods compose plausible scenes from a large object database, but overlook…

Functional 3D scene graphs offer a versatile and flexible representation for 3D scene understanding and robotic manipulation, defined by object nodes, interactive elements, and functional relationship edges. However, their potential remains…

Despite recent advancements in single-domain or single-object image generation, it is still challenging to generate complex scenes containing diverse, multiple objects and their interactions. Scene graphs, composed of nodes as objects and…

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in…

Accurate temporal prediction is the bridge between comprehensive scene understanding and embodied artificial intelligence. However, predicting multiple fine-grained states of a scene at multiple temporal scales is difficult for…

We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete…

Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…