Related papers: WonderWorld: Interactive 3D Scene Generation from …

Capturing and labeling real-world 3D data is laborious and time-consuming, which makes it costly to train strong 3D models. To address this issue, recent works present a simple method by generating randomized 3D scenes without simulation…

Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle…

Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on predefined…

Text-to-image models are showcasing the impressive ability to create high-quality and diverse generative images. Nevertheless, the transition from freehand sketches to complex scene images remains challenging using diffusion models. In this…

Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…

Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to…

Modeling scenes using video generation models has garnered growing research interest in recent years. However, most existing approaches rely on perspective video models that synthesize only limited observations of a scene, leading to issues…

We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we…

Recent advances in 3D scene representations have enabled high-fidelity novel view synthesis, yet adapting to discrete scene changes and constructing interactive 3D environments remain open challenges in vision and robotics. Existing…

3D-aware GANs aim to synthesize realistic 3D scenes such that they can be rendered in arbitrary perspectives to produce images. Although previous methods produce realistic images, they suffer from unstable training or degenerate solutions…

The significant progress on Generative Adversarial Networks (GANs) have made it possible to generate surprisingly realistic images for single object based on natural language descriptions. However, controlled generation of images for…

Building an efficient and physically consistent world model from limited observations is a long standing challenge in vision and robotics. Many existing world modeling pipelines are based on implicit generative models, which are hard to…

Generating dynamic 3D object from a single-view video is challenging due to the lack of 4D labeled data. An intuitive approach is to extend previous image-to-3D pipelines by transferring off-the-shelf image generation models such as score…

We introduce the Sphere Encoder, an efficient generative framework capable of producing images in a single forward pass and competing with many-step diffusion models using fewer than five steps. Our approach works by learning an encoder…

Generating high-fidelity, physically interactive 3D simulated tabletop scenes is essential for embodied AI -- especially for robotic manipulation policy learning and data synthesis. However, current text- or image-driven 3D scene generation…

Recent advancements in Generative Artificial Intelligence (GenAI) have significantly enhanced the capabilities of both image generation and editing. However, current approaches often treat these tasks separately, leading to inefficiencies…

In this paper, we propose VideoFrom3D, a novel framework for synthesizing high-quality 3D scene videos from coarse geometry, a camera trajectory, and a reference image. Our approach streamlines the 3D graphic design workflow, enabling…

In this work, we present SceneDreamer, an unconditional generative model for unbounded 3D scenes, which synthesizes large-scale 3D landscapes from random noise. Our framework is learned from in-the-wild 2D image collections only, without…

We present a technique for rendering highly complex 3D scenes in real-time by generating uniformly distributed points on the scene's visible surfaces. The technique is applicable to a wide range of scene types, like scenes directly based on…

Directly generating scenes from satellite imagery offers exciting possibilities for integration into applications like games and map services. However, challenges arise from significant view changes and scene scale. Previous efforts mainly…