中文
相关论文

相关论文: EditSplat: Multi-View Fusion and Attention-Guided …

200 篇论文

We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effective scene representation that enables high-quality,…

计算机视觉与模式识别 · 计算机科学 2026-04-24 Yuki Fujimura , Takahiro Kushida , Kazuya Kitano , Takuya Funatomi , Yasuhiro Mukaigawa

Over the past year, 3D Gaussian Splatting (3DGS) has received significant attention for its ability to represent 3D scenes in a perceptually accurate manner. However, it can require a substantial amount of storage since each splat's…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Brent Zoomers , Maarten Wijnants , Ivan Molenaers , Joni Vanherck , Jeroen Put , Lode Jorissen , Nick Michiels

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Peizhen Zheng , Dongjing Jiang , Qingchong Jiao , Redouane EL Bouchtaoui , Flynnwell Jianfei Zhang

Referenced-based scene stylization that edits the appearance based on a content-aligned reference image is an emerging research area. Starting with a pretrained neural radiance field (NeRF), existing methods typically learn a novel…

计算机视觉与模式识别 · 计算机科学 2024-07-11 Yiqun Mei , Jiacong Xu , Vishal M. Patel

Recent 4D dynamic scene editing methods require editing thousands of 2D images used for dynamic scene synthesis and updating the entire scene with additional training loops, resulting in several hours of processing to edit a single dynamic…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Joohyun Kwon , Hanbyel Cho , Junmo Kim

Recent progress in feed-forward 3D Gaussian Splatting (3DGS) has notably improved rendering quality. However, the spatially uniform and highly redundant 3DGS map generated by previous feed-forward 3DGS methods limits their integration into…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Zicheng Zhang , Xiangting Meng , Ke Wu , Wenchao Ding

3D Gaussian Splatting (3DGS) has recently transformed photorealistic reconstruction, achieving high visual fidelity and real-time performance. However, rendering quality significantly deteriorates when test views deviate from the camera…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Yutong Chen , Marko Mihajlovic , Xiyi Chen , Yiming Wang , Sergey Prokudin , Siyu Tang

We introduce GeoGS3D, a novel two-stage framework for reconstructing detailed 3D objects from single-view images. Inspired by the success of pre-trained 2D diffusion models, our method incorporates an orthogonal plane decomposition…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Qijun Feng , Zhen Xing , Zuxuan Wu , Yu-Gang Jiang

Conventional 3D style transfer methods rely on a fixed reference image to apply artistic patterns to 3D scenes. However, in practical applications such as virtual or augmented reality, users often prefer more flexible inputs, including…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Xingyu Miao , Xueqi Qiu , Haoran Duan , Yawen Huang , Xian Wu , Jingjing Deng , Yang Long

The recent advancements in 3D Gaussian splatting (3D-GS) have not only facilitated real-time rendering through modern GPU rasterization pipelines but have also attained state-of-the-art rendering quality. Nevertheless, despite its…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Ziyi Yang , Xinyu Gao , Yangtian Sun , Yihua Huang , Xiaoyang Lyu , Wen Zhou , Shaohui Jiao , Xiaojuan Qi , Xiaogang Jin

Feed-forward 3D Gaussian Splatting methods enable single-pass reconstruction and real-time rendering. However, they typically adopt rigid pixel-to-Gaussian or voxel-to-Gaussian pipelines that uniformly allocate Gaussians, leading to…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Injae Kim , Chaehyeon Kim , Minseong Bae , Minseok Joo , Hyunwoo J. Kim

Driving scene manipulation with sensor data is emerging as a promising alternative to traditional virtual driving simulators. However, existing frameworks struggle to generate realistic scenarios efficiently due to limited editing…

机器人学 · 计算机科学 2025-10-06 Sung-Yeon Park , Adam Lee , Juanwu Lu , Can Cui , Luyang Jiang , Rohit Gupta , Kyungtae Han , Ahmadreza Moradipari , Ziran Wang

A key challenge in fine-grained 3D-based interactive editing is the absence of an efficient representation that balances diverse modifications with high-quality view synthesis under a given memory constraint. While 3D meshes provide…

3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling in-the-wild scenes affected by…

计算机视觉与模式识别 · 计算机科学 2025-12-05 Chuanyu Fu , Guanying Chen , Yuqi Zhang , Kunbin Yao , Yuan Xiong , Chuan Huang , Shuguang Cui , Yasuyuki Matsushita , Xiaochun Cao

Diffusion-based 2D virtual try-on (VTON) techniques have recently demonstrated strong performance, while the development of 3D VTON has largely lagged behind. Despite recent advances in text-guided 3D scene editing, integrating 2D VTON into…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Yukang Cao , Masoud Hadi , Liang Pan , Ziwei Liu

Reconstructing a 3D scene from images is challenging due to the different ways light interacts with surfaces depending on the viewer's position and the surface's material. In classical computer graphics, materials can be classified as…

计算机视觉与模式识别 · 计算机科学 2025-02-03 Mateusz Nowak , Wojciech Jarosz , Peter Chin

Recently, the field of text-guided 3D scene generation has garnered significant attention. High-quality generation that aligns with physical realism and high controllability is crucial for practical 3D scene applications. However, existing…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Yang Zhou , Zongjin He , Qixuan Li , Chao Wang

TL;DR: Gaussian Splatting is a widely adopted approach for 3D scene representation, offering efficient, high-quality reconstruction and rendering. A key reason for its success is the simplicity of representing scenes with sets of Gaussians,…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Jiahuan Cheng , Jan-Nico Zaech , Luc Van Gool , Danda Pani Paudel

Novel View Synthesis (NVS) for street scenes play a critical role in the autonomous driving simulation. The current mainstream technique to achieve it is neural rendering, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting…

计算机视觉与模式识别 · 计算机科学 2024-04-01 Zhongrui Yu , Haoran Wang , Jinze Yang , Hanzhang Wang , Zeke Xie , Yunfeng Cai , Jiale Cao , Zhong Ji , Mingming Sun

Recent advancements in multi-modal 3D pre-training methods have shown promising efficacy in learning joint representations of text, images, and point clouds. However, adopting point clouds as 3D representation fails to fully capture the…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Haoyuan Li , Yanpeng Zhou , Tao Tang , Jifei Song , Yihan Zeng , Michael Kampffmeyer , Hang Xu , Xiaodan Liang