Related papers: PhysGen3D: Crafting a Miniature Interactive World …
While the generation of 3D content from single-view images has been extensively studied, the creation of physically consistent 3D dynamic scenes from videos remains in its early stages. We propose a novel framework leveraging generative 3D…
Diffusion models have achieved great success in generating 2D images. However, the quality and generalizability of 3D content generation remain limited. State-of-the-art methods often require large-scale 3D assets for training, which are…
Aided by text-to-image and text-to-video diffusion models, existing 4D content creation pipelines utilize score distillation sampling to optimize the entire dynamic 3D scene. However, as these pipelines generate 4D content from text or…
Recent advancements in 3D generation have leveraged synthetic datasets with ground truth 3D assets and predefined cameras. However, the potential of adopting real-world datasets, which can produce significantly more realistic 3D scenes,…
Digital twin worlds with realistic interactive dynamics presents a new opportunity to develop generalist embodied agents in scannable environments with complex physical behaviors. To this end, we present GDGen (Generalized Representation…
Video generation models nowadays are capable of generating visually realistic videos, but often fail to adhere to physical laws, limiting their ability to generate physically plausible videos and serve as ''world models''. To address this…
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…
We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation and…
Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of domains including spatial intelligence, embodied intelligence, and autonomous driving. While…
Single image view synthesis allows for the generation of new views of a scene given a single input image. This is challenging, as it requires comprehensively understanding the 3D scene from a single image. As a result, current methods…
Despite the latest remarkable advances in generative modeling, efficient generation of high-quality 3D assets from textual prompts remains a difficult task. A key challenge lies in data scarcity: the most extensive 3D datasets encompass…
3D scene generation seeks to synthesize spatially structured, semantically meaningful, and photorealistic environments for applications such as immersive media, robotics, autonomous driving, and embodied AI. Early methods based on…
Generating immersive 3D scenes from texts is a core task in computer vision, crucial for applications in virtual reality and game development. Despite the promise of leveraging 2D diffusion priors, existing methods suffer from spatial…
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…
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions. We investigate the task of unconditionally synthesizing unbounded nature scenes,…
Modern 3D generation methods can rapidly create shapes from sparse or single views, but their outputs often lack geometric detail due to computational constraints. We present DetailGen3D, a generative approach specifically designed to…
Understanding the dynamic physical world, characterized by its evolving 3D structure, real-world motion, and semantic content with textual descriptions, is crucial for human-agent interaction and enables embodied agents to perceive and act…
Unsupervised generation of 3D-aware clothed humans with various appearances and controllable geometries is important for creating virtual human avatars and other AR/VR applications. Existing methods are either limited to rigid object…
Despite advances in physics-based 3D motion synthesis, current methods face key limitations: reliance on pre-reconstructed 3D Gaussian Splatting (3DGS) built from dense multi-view images with time-consuming per-scene optimization; physics…
We present StdGEN, an innovative pipeline for generating semantically decomposed high-quality 3D characters from single images, enabling broad applications in virtual reality, gaming, and filmmaking, etc. Unlike previous methods which…