Related papers: Compositional Generative Model of Unbounded 4D Cit…
Compositing an object into an image involves multiple non-trivial sub-tasks such as object placement and scaling, color/lighting harmonization, viewpoint/geometry adjustment, and shadow/reflection generation. Recent generative image…
We present LT3SD, a novel latent diffusion model for large-scale 3D scene generation. Recent advances in diffusion models have shown impressive results in 3D object generation, but are limited in spatial extent and quality when extended to…
Reconstructing urban scenes is challenging due to their complex geometries and the presence of potentially dynamic objects. 3D Gaussian Splatting (3DGS)-based methods have shown strong performance, but existing approaches often incorporate…
In this paper, we explore the task of generating expansive outdoor scenes, ranging from castles to high-rises. Unlike indoor scene generation, which has been a primary focus of prior work, outdoor scene generation presents unique…
With the onset of diffusion-based generative models and their ability to generate text-conditioned images, content generation has received a massive invigoration. Recently, these models have been shown to provide useful guidance for the…
Advances in 3D generation have facilitated sequential 3D model generation (a.k.a 4D generation), yet its application for animatable objects with large motion remains scarce. Our work proposes AnimatableDreamer, a text-to-4D generation…
Realistic 3D city generation is fundamental to a wide range of applications, including virtual reality and digital twins. However, most existing methods rely on training a single diffusion model, which limits their ability to generate…
This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the…
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…
4D generation, or dynamic 3D content generation, integrates spatial, temporal, and view dimensions to model realistic dynamic scenes, playing a foundational role in advancing world models and physical AI. However, maintaining long-chain…
Spatio-temporal scene graphs provide a principled representation for modeling evolving object interactions, yet existing methods remain fundamentally frame-centric: they reason only about currently visible objects, discard entities upon…
Generating high-fidelity, controllable, and annotated training data is critical for autonomous driving. Existing methods typically generate a single data form directly from a coarse scene layout, which not only fails to output rich data…
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…
Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial…
The latest emerged 4D Panoptic Scene Graph (4D-PSG) provides an advanced-ever representation for comprehensively modeling the dynamic 4D visual real world. Unfortunately, current pioneering 4D-PSG research can primarily suffer from data…
We present Tensor4D, an efficient yet effective approach to dynamic scene modeling. The key of our solution is an efficient 4D tensor decomposition method so that the dynamic scene can be directly represented as a 4D spatio-temporal tensor.…
Autonomous trajectory generation for unmanned aerial vehicles (UAVs) in unknown environments continues to be an important research area as UAVs become more prolific. We define a trajectory generation algorithm for a vehicle in an unknown…
Video-conditioned 4D shape generation aims to recover time-varying 3D geometry and view-consistent appearance directly from an input video. In this work, we introduce a native video-to-4D shape generation framework that synthesizes a single…
We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models. Our key…
We introduce a method to generate 3D scenes that are disentangled into their component objects. This disentanglement is unsupervised, relying only on the knowledge of a large pretrained text-to-image model. Our key insight is that objects…