中文
相关论文

相关论文: OmniX: From Unified Panoramic Generation and Perce…

200 篇论文

We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene. Such a model can be used to produce 3D "remixes" of a given scene, by mapping spatial latent codes into a 3D volumetric…

计算机视觉与模式识别 · 计算机科学 2022-11-29 Animesh Karnewar , Oliver Wang , Tobias Ritschel , Niloy Mitra

We propose a decoupled 3D scene generation framework called SceneMaker in this work. Due to the lack of sufficient open-set de-occlusion and pose estimation priors, existing methods struggle to simultaneously produce high-quality geometry…

计算机视觉与模式识别 · 计算机科学 2025-12-12 Yukai Shi , Weiyu Li , Zihao Wang , Hongyang Li , Xingyu Chen , Ping Tan , Lei Zhang

We introduce a novel method for generating 360{\deg} panoramas from text prompts or images. Our approach leverages recent advances in 3D generation by employing multi-view diffusion models to jointly synthesize the six faces of a cubemap.…

计算机视觉与模式识别 · 计算机科学 2025-01-29 Nikolai Kalischek , Michael Oechsle , Fabian Manhardt , Philipp Henzler , Konrad Schindler , Federico Tombari

Recent progress in 3D/4D scene generation emphasizes the importance of physical alignment throughout video generation and scene reconstruction. However, existing methods improve the alignment separately at each stage, making it difficult to…

计算机视觉与模式识别 · 计算机科学 2025-07-31 Byeongjun Park , Hyojun Go , Hyelin Nam , Byung-Hoon Kim , Hyungjin Chung , Changick Kim

We introduce OmniRe, a comprehensive system for efficiently creating high-fidelity digital twins of dynamic real-world scenes from on-device logs. Recent methods using neural fields or Gaussian Splatting primarily focus on vehicles,…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Ziyu Chen , Jiawei Yang , Jiahui Huang , Riccardo de Lutio , Janick Martinez Esturo , Boris Ivanovic , Or Litany , Zan Gojcic , Sanja Fidler , Marco Pavone , Li Song , Yue Wang

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…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Yanxu Meng , Haoning Wu , Ya Zhang , Weidi Xie

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…

计算机视觉与模式识别 · 计算机科学 2026-01-28 Jisheng Chu , Wenrui Li , Rui Zhao , Wangmeng Zuo , Shifeng Chen , Xiaopeng Fan

Comprehensive modeling of the surrounding 3D world is key to the success of autonomous driving. However, existing perception tasks like object detection, road structure segmentation, depth & elevation estimation, and open-set object…

计算机视觉与模式识别 · 计算机科学 2023-06-19 Yuqi Wang , Yuntao Chen , Xingyu Liao , Lue Fan , Zhaoxiang Zhang

Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Seung Wook Kim , Bradley Brown , Kangxue Yin , Karsten Kreis , Katja Schwarz , Daiqing Li , Robin Rombach , Antonio Torralba , Sanja Fidler

Generating high-quality, textured 3D scenes from a single image remains a fundamental challenge in vision and graphics. Recent image-to-3D generators recover reasonable geometry from single views, but their object-centric training limits…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Kaizhi Zheng , Yue Fan , Jing Gu , Zishuo Xu , Xuehai He , Xin Eric Wang

Unsupervised learning of object-centric representations in dynamic visual scenes is challenging. Unlike most previous approaches that learn to decompose 2D images, we present DynaVol, a 3D scene generative model that unifies geometric…

计算机视觉与模式识别 · 计算机科学 2024-01-29 Yanpeng Zhao , Siyu Gao , Yunbo Wang , Xiaokang Yang

We introduce CinemaWorld, a generative augmented reality system that augments the viewer's physical surroundings with automatically generated mixed reality 3D content extracted from and synchronized with 2D movie scenes. Our system…

人机交互 · 计算机科学 2026-03-10 Keiichi Ihara , DaeHo Lee , Manato Abe , Hye-Young Jo , Ryo Suzuki

Creating large-scale interactive 3D environments is essential for the development of Robotics and Embodied AI research. Current methods, including manual design, procedural generation, diffusion-based scene generation, and large language…

计算机视觉与模式识别 · 计算机科学 2024-11-18 Yian Wang , Xiaowen Qiu , Jiageng Liu , Zhehuan Chen , Jiting Cai , Yufei Wang , Tsun-Hsuan Wang , Zhou Xian , Chuang Gan

Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the…

计算机视觉与模式识别 · 计算机科学 2016-02-12 Helge Rhodin , Nadia Robertini , Christian Richardt , Hans-Peter Seidel , Christian Theobalt

We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Jin Cao , Hong-Xing Yu , Jiajun Wu

Generating immersive 360{\deg} indoor panoramas from 2D top-down views has applications in virtual reality, interior design, real estate, and robotics. This task is challenging due to the lack of explicit 3D structure and the need for…

计算机视觉与模式识别 · 计算机科学 2025-07-30 Zitong Zhang , Suranjan Gautam , Rui Yu

The generation of 3D scenes from user-specified conditions offers a promising avenue for alleviating the production burden in 3D applications. Previous studies required significant effort to realize the desired scene, owing to limited…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Takayuki Hara , Tatsuya Harada

Generating realistic 3D indoor scenes from user inputs remains a challenging problem in computer vision and graphics, requiring careful balance of geometric consistency, spatial relationships, and visual realism. While neural generation…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Mengqi Zhou , Xipeng Wang , Yuxi Wang , Zhaoxiang Zhang

Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360{\deg} scene from a single image remains a highly ill-posed and challenging problem. Recent approaches have…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Runmao Yao , Junsheng Zhou , Zhen Dong , Yu-Shen Liu

Generating 4D scenes from a single-view video is inherently ill-posed: a single viewpoint lacks the information needed to recover a complete, dynamic scene with full coverage. Existing methods are typically limited to monocular videos,…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Tingxi Chen , Ke Hao , Yabo Chen , Zhengxue Cheng , Rong Xie , Li Song , Haibin Huang , Chi Zhang , Xuelong Li