中文
相关论文

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

200 篇论文

Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidelity and efficient representation that links the latent space…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Haitao Yang , Yuan Dong , Hanwen Jiang , Dejia Xu , Georgios Pavlakos , Qixing Huang

Humans have a remarkable ability to predict the effect of physical interactions on the dynamics of objects. Endowing machines with this ability would allow important applications in areas like robotics and autonomous vehicles. In this work,…

计算机视觉与模式识别 · 计算机科学 2019-01-03 Davis Rempe , Srinath Sridhar , He Wang , Leonidas J. Guibas

Scene representations using 3D Gaussian primitives have produced excellent results in modeling the appearance of static and dynamic 3D scenes. Many graphics applications, however, demand the ability to manipulate both the appearance and the…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Ri-Zhao Qiu , Ge Yang , Weijia Zeng , Xiaolong Wang

Forecasting a typical object's future motion is a critical task for interpreting and interacting with dynamic environments in computer vision. Event-based sensors, which could capture changes in the scene with exceptional temporal…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Song Wu , Zhiyu Zhu , Junhui Hou , Guangming Shi , Jinjian Wu

High-quality 3D assets for traffic participants are critical for multi-sensor simulation, which is essential for the safe end-to-end development of autonomy. Building assets from in-the-wild data is key for diversity and realism, but…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Ze Yang , Jingkang Wang , Haowei Zhang , Sivabalan Manivasagam , Yun Chen , Raquel Urtasun

Reconstructing photorealistic and animatable 4D head avatars from a single portrait image remains a fundamental challenge in computer vision. While diffusion models have enabled remarkable progress in image and video generation for avatar…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Chao Xu , Xiaochen Zhao , Xiang Deng , Jingxiang Sun , Donglin Di , Zhuo Su , Yebin Liu

Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models from limited real-world video data, especially for…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Yu Yang , Zhilu Zhang , Xiang Zhang , Yihan Zeng , Hui Li , Wangmeng Zuo

Recently, 3D Gaussian Splatting (3DGS), an explicit scene representation technique, has shown significant promise for dynamic novel-view synthesis from monocular video input. However, purely data-driven 3DGS often struggles to capture the…

计算机视觉与模式识别 · 计算机科学 2025-12-05 Haoqin Hong , Ding Fan , Fubin Dou , Zhi-Li Zhou , Haoran Sun , Congcong Zhu , Jingrun Chen

Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such capacity remains a challenging task due to the difficulty in…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Jianhao Yuan , Fabio Pizzati , Francesco Pinto , Lars Kunze , Ivan Laptev , Paul Newman , Philip Torr , Daniele De Martini

Video generation models have progressed tremendously through large latent diffusion transformers trained with rectified flow techniques. Yet these models still struggle with geometric inconsistencies, unstable motion, and visual artifacts…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Orest Kupyn , Fabian Manhardt , Federico Tombari , Christian Rupprecht

We propose a method to enhance 3D Gaussian Splatting (3DGS)~\cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Xingjun Wang , Lianlei Shan

We present a novel framework for generating photorealistic 3D human head and subsequently manipulating and reposing them with remarkable flexibility. The proposed approach leverages an implicit function representation of 3D human heads,…

计算机视觉与模式识别 · 计算机科学 2023-12-22 Yushi Lan , Feitong Tan , Di Qiu , Qiangeng Xu , Kyle Genova , Zeng Huang , Sean Fanello , Rohit Pandey , Thomas Funkhouser , Chen Change Loy , Yinda Zhang

Video deblurring presents a considerable challenge owing to the complexity of blur, which frequently results from a combination of camera shakes, and object motions. In the field of video deblurring, many previous works have primarily…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Haoyang Long , Yan Wang , Wendong Wang

Predicting human motion plays a crucial role in ensuring a safe and effective human-robot close collaboration in intelligent remanufacturing systems of the future. Existing works can be categorized into two groups: those focusing on…

机器人学 · 计算机科学 2023-08-01 Sibo Tian , Minghui Zheng , Xiao Liang

Existing diffusion-based text-to-3D generation methods primarily focus on producing visually realistic shapes and appearances, often neglecting the physical constraints necessary for downstream tasks. Generated models frequently fail to…

机器学习 · 计算机科学 2024-11-19 Yunuo Chen , Tianyi Xie , Zeshun Zong , Xuan Li , Feng Gao , Yin Yang , Ying Nian Wu , Chenfanfu Jiang

Text-to-3D generation has shown great promise in generating novel 3D content based on given text prompts. However, existing generative methods mostly focus on geometric or visual plausibility while ignoring precise physics perception for…

计算机视觉与模式识别 · 计算机科学 2024-03-20 Qingshan Xu , Jiao Liu , Melvin Wong , Caishun Chen , Yew-Soon Ong

Accurately reconstructing a 3D scene including explicit geometry information is both attractive and challenging. Geometry reconstruction can benefit from incorporating differentiable appearance models, such as Neural Radiance Fields and 3D…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Ancheng Lin , Yusheng Xiang , Paul Kennedy , Jun Li

3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with…

计算机视觉与模式识别 · 计算机科学 2024-04-18 Zhiheng Liu , Hao Ouyang , Qiuyu Wang , Ka Leong Cheng , Jie Xiao , Kai Zhu , Nan Xue , Yu Liu , Yujun Shen , Yang Cao

Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models. These models are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Zeyu Yang , Zijie Pan , Chun Gu , Li Zhang

This paper introduces a novel clothed human model that can be learned from multiview RGB videos, with a particular emphasis on recovering physically accurate body and cloth movements. Our method, Position Based Dynamic Gaussians (PBDyG),…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Shota Sasaki , Jane Wu , Ko Nishino