Related papers: PAT3D: Physics-Augmented Text-to-3D Scene Generati…

We present a system for generating indoor scenes in response to text prompts. The prompts are not limited to a fixed vocabulary of scene descriptions, and the objects in generated scenes are not restricted to a fixed set of object…

A comprehensive semantic understanding of a scene is important for many applications - but in what space should diverse semantic information (e.g., objects, scene categories, material types, texture, etc.) be grounded and what should be its…

Recent advances in large language models (LLMs) have significantly improved language-driven 3D content generation, but most existing approaches still treat scene generation and user interaction as separate processes, limiting the…

Recently, 3D generative models have made impressive progress, enabling the generation of almost arbitrary 3D assets from text or image inputs. However, these approaches generate objects in isolation without any consideration for the scene…

3D scene graphs have recently emerged as a powerful high-level representation of 3D environments. A 3D scene graph describes the environment as a layered graph where nodes represent spatial concepts at multiple levels of abstraction and…

Current compositional image-to-3D scene generation approaches construct 3D scenes by time-consuming iterative layout optimization or inflexible joint object-layout generation. Moreover, most methods rely on limited field-of-view perspective…

We present SceneNAT, a single-stage masked non-autoregressive Transformer that synthesizes complete 3D indoor scenes from natural language instructions through only a few parallel decoding passes, offering improved performance and…

GenerateCT, the first approach to generating 3D medical imaging conditioned on free-form medical text prompts, incorporates a text encoder and three key components: a novel causal vision transformer for encoding 3D CT volumes, a text-image…

Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and…

Scene synthesis and editing has emerged as a promising direction in computer graphics. Current trained approaches for 3D indoor scene generation either oversimplify object semantics through one-hot class encodings (e.g., 'chair' or…

As several industries are moving towards modeling massive 3D virtual worlds, the need for content creation tools that can scale in terms of the quantity, quality, and diversity of 3D content is becoming evident. In our work, we aim to train…

Given a visual scene, humans have strong intuitions about how a scene can evolve over time under given actions. The intuition, often termed visual intuitive physics, is a critical ability that allows us to make effective plans to manipulate…

3D content generation has recently attracted significant research interest, driven by its critical applications in VR/AR and embodied AI. In this work, we tackle the challenging task of synthesizing multiple 3D assets within a single scene…

Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR, where functional part decomposition and kinematic motion are essential. Yet producing high-fidelity articulated assets remains…

Automatic 3D content creation has achieved rapid progress recently due to the availability of pre-trained, large language models and image diffusion models, forming the emerging topic of text-to-3D content creation. Existing text-to-3D…

3D Gaussian Splatting has achieved remarkable success in reconstructing both static and dynamic 3D scenes. However, in a scene represented by 3D Gaussian primitives, interactions between objects suffer from inaccurate 3D segmentation,…

The creation of complex 3D scenes tailored to user specifications has been a tedious and challenging task with traditional 3D modeling tools. Although some pioneering methods have achieved automatic text-to-3D generation, they are generally…

Text-to-3D asset generation has achieved significant optimization under the supervision of 2D diffusion priors. However, when dealing with compositional scenes, existing methods encounter several challenges: 1). failure to ensure that…

Existing image-to-video generation methods often produce physically implausible motions and lack precise control over object dynamics. While prior approaches have incorporated physics simulators, they remain confined to 2D planar motions…

3D semantic scene graphs are a powerful holistic representation as they describe the individual objects and depict the relation between them. They are compact high-level graphs that enable many tasks requiring scene reasoning. In real-world…