中文
相关论文

相关论文: OmniSplat: Taming Feed-Forward 3D Gaussian Splatti…

200 篇论文

Photorealistic reconstruction relying on 3D Gaussian Splatting has shown promising potential in various domains. However, the current 3D Gaussian Splatting system only supports radiance field reconstruction using undistorted perspective…

计算机视觉与模式识别 · 计算机科学 2024-11-07 Longwei Li , Huajian Huang , Sai-Kit Yeung , Hui Cheng

We introduce AnySplat, a feed forward network for novel view synthesis from uncalibrated image collections. In contrast to traditional neural rendering pipelines that demand known camera poses and per scene optimization, or recent feed…

计算机视觉与模式识别 · 计算机科学 2025-09-16 Lihan Jiang , Yucheng Mao , Linning Xu , Tao Lu , Kerui Ren , Yichen Jin , Xudong Xu , Mulin Yu , Jiangmiao Pang , Feng Zhao , Dahua Lin , Bo Dai

This paper presents a pose-free, feed-forward 3D Gaussian Splatting (3DGS) framework designed to handle unfavorable input views. A common rendering setup for training feed-forward approaches places a 3D object at the world origin and…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Yuki Fujimura , Takahiro Kushida , Kazuya Kitano , Takuya Funatomi , Yasuhiro Mukaigawa

Omnidirectional (or 360-degree) images are increasingly being used for 3D applications since they allow the rendering of an entire scene with a single image. Existing works based on neural radiance fields demonstrate successful 3D…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Suyoung Lee , Jaeyoung Chung , Jaeyoo Huh , Kyoung Mu Lee

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

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

Feed-forward 3D Gaussian Splatting (3DGS) enables efficient one-pass scene reconstruction, providing 3D representations for novel view synthesis without per-scene optimization. However, existing methods typically predict pixel-aligned…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Jongmin Park , Minh-Quan Viet Bui , Juan Luis Gonzalez Bello , Jaeho Moon , Jihyong Oh , Munchurl Kim

The recent development of feedforward 3D Gaussian Splatting (3DGS) presents a new paradigm to reconstruct 3D scenes. Using neural networks trained on large-scale multi-view datasets, it can directly infer 3DGS representations from sparse…

计算机视觉与模式识别 · 计算机科学 2025-06-12 Zetian Song , Jiaye Fu , Jiaqi Zhang , Xiaohan Lu , Chuanmin Jia , Siwei Ma , Wen Gao

The efficient spatial allocation of primitives serves as the foundation of 3D Gaussian Splatting, as it directly dictates the synergy between representation compactness, reconstruction speed, and rendering fidelity. Previous solutions,…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Roni Itkin , Noam Issachar , Yehonatan Keypur , Xingyu Chen , Anpei Chen , Sagie Benaim

We consider the problem of novel view synthesis from unposed images in a single feed-forward. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstruction and view synthesis capabilities of 3DGS, where we further…

计算机视觉与模式识别 · 计算机科学 2025-07-25 Sunghwan Hong , Jaewoo Jung , Heeseong Shin , Jisang Han , Jiaolong Yang , Chong Luo , Seungryong Kim

Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is mapped to a 3D…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Weijie Wang , Yeqing Chen , Zeyu Zhang , Hengyu Liu , Haoxiao Wang , Zhiyuan Feng , Wenkang Qin , Feng Chen , Zheng Zhu , Donny Y. Chen , Bohan Zhuang

High-fidelity three-dimensional (3D) reconstruction is essential for robotics and simulation. While Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) achieve impressive rendering quality, their reliance on time-consuming…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Xiong Jinlin , Li Can , Shen Jiawei , Qi Zhigang , Sun Lei , Zhao Dongyang

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

Recent advancements in 3D content generation from text or a single image struggle with limited high-quality 3D datasets and inconsistency from 2D multi-view generation. We introduce DiffSplat, a novel 3D generative framework that natively…

计算机视觉与模式识别 · 计算机科学 2025-01-29 Chenguo Lin , Panwang Pan , Bangbang Yang , Zeming Li , Yadong Mu

Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Ziyue Zhu , Zhanqian Wu , Zhenxin Zhu , Lijun Zhou , Haiyang Sun , Bing Wan , Kun Ma , Guang Chen , Hangjun Ye , Jin Xie , jian Yang

We present ViewSplat, a view-adaptive 3D Gaussian splatting network for novel view synthesis from unposed images. While recent feed-forward 3D Gaussian splatting has significantly accelerated 3D scene reconstruction by bypassing per-scene…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Moonyeon Jeong , Seunggi Min , Suhyeon Lee , Hongje Seong

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Jiaqi Yao , Zhongmiao Yan , Jingyi Xu , Songpengcheng Xia , Yan Xiang , Ling Pei

Feed-forward 3D Gaussian Splatting (3DGS) has shown great promise for real-time novel view synthesis, but its application to panoramic imagery remains challenging. Existing methods often rely on multi-view cost volumes for geometric…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Qiwei Wang , Xianghui Ze , Jingyi Yu , Yujiao Shi

Feed-forward 3D Gaussian Splatting models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is fundamentally hindered by the scarcity of large-scale 3D annotations. A practical compromise is…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Yuke Li , Weihang Liu , Cheng Zhang , Yuefeng Zhang , Jiadi Cui , Zixuan Wang , Junran Ding , Haoyu Wu , Yujiao Shi , Jingyi Yu , Xin Lou

Recently, generalizable feed-forward methods based on 3D Gaussian Splatting have gained significant attention for their potential to reconstruct 3D scenes using finite resources. These approaches create a 3D radiance field, parameterized by…

计算机视觉与模式识别 · 计算机科学 2025-02-04 Wonseok Roh , Hwanhee Jung , Jong Wook Kim , Seunggwan Lee , Innfarn Yoo , Andreas Lugmayr , Seunggeun Chi , Karthik Ramani , Sangpil Kim
‹ 上一页 1 2 3 10 下一页 ›