中文
相关论文

相关论文: DrivingForward: Feed-forward 3D Gaussian Splatting…

200 篇论文

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

Feed-forward surround-view autonomous driving scene reconstruction offers fast, generalizable inference ability, which faces the core challenge of ensuring generalization while elevating novel view quality. Due to the surround-view with…

计算机视觉与模式识别 · 计算机科学 2025-10-23 Junhong Lin , Kangli Wang , Shunzhou Wang , Songlin Fan , Ge Li , Wei Gao

Recent advances in 3D Gaussian Splatting (3DGS) have enabled significant progress in photorealistic novel view synthesis. However, traditional 3DGS relies on a slow, iterative optimization process, which limits its use in scenarios…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Can Wang , Lei Liu , Wei Jiang , Dong Xu

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

Feed-forward 3D Gaussian Splatting methods have achieved impressive reconstruction quality for autonomous driving scenes, yet they entangle scene geometry with transient appearance properties such as lighting, weather, and time of day. This…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Quentin Herau , Tianshuo Xu , Depu Meng , Jiezhi Yang , Chensheng Peng , Spencer Sherk , Yihan Hu , Wei Zhan

Novel-view synthesis and 3D reconstruction from sparse posed images are central to robotics and AR/VR. Yet, feed-forward 3D Gaussian reconstruction fails under lowlight due to noise, color shifts, and unreliable correspondence. We propose…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Fuzhen Jiang , Zengtian Xie , Zhuoran Li

Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline and rely on time-consuming iterative processes, limiting…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Hao Lu , Tianshuo Xu , Wenzhao Zheng , Yunpeng Zhang , Wei Zhan , Dalong Du , Masayoshi Tomizuka , Kurt Keutzer , Yingcong Chen

Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We…

计算机视觉与模式识别 · 计算机科学 2025-03-27 Sheng Miao , Jiaxin Huang , Dongfeng Bai , Xu Yan , Hongyu Zhou , Yue Wang , Bingbing Liu , Andreas Geiger , Yiyi Liao

A major breakthrough in 3D reconstruction is the feedforward paradigm to generate pixel-wise 3D points or Gaussian primitives from sparse, unposed images. To further incorporate semantics while avoiding the significant memory and storage…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Yu Sheng , Jiajun Deng , Xinran Zhang , Yu Zhang , Bei Hua , Yanyong Zhang , Jianmin Ji

We present FRUC, a feed-forward 3D Gaussian splatting framework for dynamic scene reconstruction from uncalibrated collaborative driving views. Existing multi-agent reconstruction frameworks are often hindered by rigid prerequisites,…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Yihang Tao , Yu Guo , Zhengru Fang , Haonan An , Yuguang Fang

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

This paper focuses on scene reconstruction under nighttime conditions in autonomous driving simulation. Recent methods based on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) have achieved photorealistic modeling in…

计算机视觉与模式识别 · 计算机科学 2026-02-17 Tae-Kyeong Kim , Xingxin Chen , Guile Wu , Chengjie Huang , Dongfeng Bai , Bingbing Liu

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

We present a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation that operates directly on multi-view RGB images and their associated SMPL-X poses. Unlike prior methods that rely on…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Devdoot Chatterjee , Zakaria Laskar , C. V. Jawahar

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

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 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

Online novel view synthesis remains challenging, requiring robust scene reconstruction from sequential, often unposed, observations. We present ReCoSplat, an autoregressive feed-forward Gaussian Splatting model supporting posed or unposed…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Freeman Cheng , Botao Ye , Xueting Li , Junqi You , Fangneng Zhan , Ming-Hsuan Yang

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

Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. Recent approaches leverage generalizable models to generate 3D scenes using 3D…

计算机视觉与模式识别 · 计算机科学 2026-02-04 Bing He , Jingnan Gao , Yunuo Chen , Ning Cao , Gang Chen , Zhengxue Cheng , Li Song , Wenjun Zhang