中文
相关论文

相关论文: Physics3D: Learning Physical Properties of 3D Gaus…

200 篇论文

Recent text-to-3D methods employing diffusion models have made significant advancements in 3D human generation. However, these approaches face challenges due to the limitations of text-to-image diffusion models, which lack an understanding…

计算机视觉与模式识别 · 计算机科学 2023-11-30 Xin Huang , Ruizhi Shao , Qi Zhang , Hongwen Zhang , Ying Feng , Yebin Liu , Qing Wang

Humanoid robots can benefit from their similarity to the human shape by learning from humans. When humans teach other humans how to perform actions, they often demonstrate the actions, and the learning human imitates the demonstration to…

机器人学 · 计算机科学 2024-10-07 Josua Spisak , Matthias Kerzel , Stefan Wermter

3D Gaussian Splatting (3DGS) has emerged as a powerful and efficient 3D representation for novel view synthesis. This paper extends 3DGS capabilities to inpainting, where masked objects in a scene are replaced with new contents that blend…

计算机视觉与模式识别 · 计算机科学 2025-04-28 Mingxuan Cui , Qing Guo , Yuyi Wang , Hongkai Yu , Di Lin , Qin Zou , Ming-Ming Cheng , Xi Li

Gaussian Splatting has become a popular technique for various 3D Computer Vision tasks, including novel view synthesis, scene reconstruction, and dynamic scene rendering. However, the challenge of natural-looking object insertion, where the…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Vsevolod Skorokhodov , Nikita Durasov , Pascal Fua

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,…

图形学 · 计算机科学 2025-06-10 Zeyu Xiao , Zhenyi Wu , Mingyang Sun , Qipeng Yan , Yufan Guo , Zhuoer Liang , Lihua Zhang

Recovering 3D scenes from sparse views is a challenging task due to its inherent ill-posed problem. Conventional methods have developed specialized solutions (e.g., geometry regularization or feed-forward deterministic model) to mitigate…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Hanyang Wang , Fangfu Liu , Jiawei Chi , Yueqi Duan

Humans are able to make rich predictions about the future dynamics of physical objects from a glance. On the other hand, most existing computer vision approaches require strong assumptions about the underlying system, ad-hoc modeling, or…

神经与进化计算 · 计算机科学 2018-09-19 Zhihua Wang , Stefano Rosa , Yishu Miao , Zihang Lai , Linhai Xie , Andrew Markham , Niki Trigoni

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained…

3D Gaussian Splatting has made a marked impact on neural rendering by achieving impressive fidelity and performance. Despite this achievement, however, it is not readily applicable to developing interactive applications. Real-time…

图形学 · 计算机科学 2024-03-01 Xiangzhi Eric Wang , Zackary P. T. Sin

Diffusion models have marked a significant milestone in the enhancement of image and video generation technologies. However, generating videos that precisely retain the shape and location of moving objects such as robots remains a…

机器人学 · 计算机科学 2024-07-04 Peng Wang , Zhihao Guo , Abdul Latheef Sait , Minh Huy Pham

Knowledge of the physical material properties governing the dynamics of a real-world object becomes necessary to accurately anticipate its response to unseen interactions. Existing methods for estimating such physical material parameters…

计算机视觉与模式识别 · 计算机科学 2025-12-19 Norika Wada , Kohei Yamashita , Ryo Kawahara , Ko Nishino

Recent advances in diffusion models have made significant progress in digital human generation. However, most existing models still struggle to maintain 3D consistency, temporal coherence, and motion accuracy. A key reason for these…

图形学 · 计算机科学 2025-03-21 Xuan Gao , Jingtao Zhou , Dongyu Liu , Yuqi Zhou , Juyong Zhang

Text-to-3D, known for its efficient generation methods and expansive creative potential, has garnered significant attention in the AIGC domain. However, the pixel-wise rendering of NeRF and its ray marching light sampling constrain the…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Xinhai Li , Huaibin Wang , Kuo-Kun Tseng

3D Gaussians, as a low-level scene representation, typically involve thousands to millions of Gaussians. This makes it difficult to control the scene in ways that reflect the underlying dynamic structure, where the number of independent…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Yunchao Zhang , Guandao Yang , Leonidas Guibas , Yanchao Yang

Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by…

计算机视觉与模式识别 · 计算机科学 2024-03-21 Pengxiang Li , Kai Chen , Zhili Liu , Ruiyuan Gao , Lanqing Hong , Guo Zhou , Hua Yao , Dit-Yan Yeung , Huchuan Lu , Xu Jia

Humans intuitively recognize objects' physical properties and predict their motion, even when the objects are engaged in complicated interactions. The abilities to perform physical reasoning and to adapt to new environments, while intrinsic…

Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Qihang Zhang , Shuangfei Zhai , Miguel Angel Bautista , Kevin Miao , Alexander Toshev , Joshua Susskind , Jiatao Gu

3D scene generation is a core technology for gaming, film/VFX, and VR/AR. Growing demand for rapid iteration, high-fidelity detail, and accessible content creation has further increased interest in this area. Existing methods broadly follow…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Haozhi Zhu , Miaomiao Zhao , Dingyao Liu , Runze Tian , Yan Zhang , Jie Guo , Fenggen Yu

Generative models have shown great promise in generating 3D geometric systems, which is a fundamental problem in many natural science domains such as molecule and protein design. However, existing approaches only operate on static…

计算机视觉与模式识别 · 计算机科学 2024-10-18 Jiaqi Han , Minkai Xu , Aaron Lou , Haotian Ye , Stefano Ermon

3D Gaussian Splatting (3DGS) has become a powerful representation for image-based object reconstruction, yet its performance drops sharply in sparse-view settings. Prior works address this limitation by employing diffusion models to repair…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Hung Nguyen , Runfa Li , An Le , Truong Nguyen