中文
相关论文

相关论文: Unifying Appearance Codes and Bilateral Grids for …

200 篇论文

We propose GGS, a Generalizable Gaussian Splatting method for Autonomous Driving which can achieve realistic rendering under large viewpoint changes. Previous generalizable 3D gaussian splatting methods are limited to rendering novel views…

计算机视觉与模式识别 · 计算机科学 2024-09-05 Huasong Han , Kaixuan Zhou , Xiaoxiao Long , Yusen Wang , Chunxia Xiao

In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis.…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Deming Li , Kaiwen Jiang , Yutao Tang , Ravi Ramamoorthi , Rama Chellappa , Cheng Peng

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

While surface-based view synthesis algorithms are appealing due to their low computational requirements, they often struggle to reproduce thin structures. In contrast, more expensive methods that model the scene's geometry as a volumetric…

Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…

Sensor simulation is pivotal for scalable validation of autonomous driving systems, yet existing Neural Radiance Fields (NeRF) based methods face applicability and efficiency challenges in industrial workflows. This paper introduces a…

Scene view synthesis, which generates novel views from limited perspectives, is increasingly vital for applications like virtual reality, augmented reality, and robotics. Unlike object-based tasks, such as generating 360{\deg} views of a…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Xiaofeng Jin , Yan Fang , Matteo Frosi , Jianfei Ge , Jiangjian Xiao , Matteo Matteucci

It is desirable to create 3D object models and 3D maps from 2D input images for applications such as navigation, virtual tourism, and urban planning. The traditional methods of creating 3D maps, (such as photogrammetry), require a large…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Sai Tarun Sathyan , Thomas B. Kinsman

Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention…

计算机视觉与模式识别 · 计算机科学 2025-03-04 You Shen , Zhipeng Zhang , Xinyang Li , Yansong Qu , Yu Lin , Shengchuan Zhang , Liujuan Cao

3D Gaussian Splatting (3DGS) has recently emerged as a powerful explicit representation enabling fast, high-fidelity rendering, making it a promising foundation for closed-loop simulators and perception models in autonomous driving.…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Kota Shimomura , Hidehisa Arai , Tsubasa Takahashi , Takayoshi Yamashita , Hironobu Fujiyoshi

We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios. Our approach employs a two-stage optimization…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Chensheng Peng , Chengwei Zhang , Yixiao Wang , Chenfeng Xu , Yichen Xie , Wenzhao Zheng , Kurt Keutzer , Masayoshi Tomizuka , Wei Zhan

Novel view synthesis (NVS) is crucial in computer vision and graphics, with wide applications in AR, VR, and autonomous driving. While 3D Gaussian Splatting (3DGS) enables real-time rendering with high appearance fidelity, it suffers from…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Yancheng Zhang , Guangyu Sun , Chen Chen

The integration of aerial and ground images has been a promising solution in 3D modeling of complex scenes, which is seriously restricted by finding reliable correspondences. The primary contribution of this study is a feature matching…

计算机视觉与模式识别 · 计算机科学 2025-09-25 Jiangxue Yu , Hui Wang , San Jiang , Xing Zhang , Dejin Zhang , Qingquan Li

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

We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire…

计算机视觉与模式识别 · 计算机科学 2024-03-21 Xiaoyu Zhou , Zhiwei Lin , Xiaojun Shan , Yongtao Wang , Deqing Sun , Ming-Hsuan Yang

Neural Radiance Fields (NeRFs) have demonstrated the remarkable potential of neural networks to capture the intricacies of 3D objects. By encoding the shape and color information within neural network weights, NeRFs excel at producing…

计算机视觉与模式识别 · 计算机科学 2024-06-13 Dawid Malarz , Weronika Smolak , Jacek Tabor , Sławomir Tadeja , Przemysław Spurek

Scene reconstruction has emerged as a central challenge in computer vision, with approaches such as Neural Radiance Fields (NeRF) and Gaussian Splatting achieving remarkable progress. While Gaussian Splatting demonstrates strong performance…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Alexander Valverde , Brian Xu , Yuyin Zhou , Meng Xu , Hongyun Wang

Neural Radiance Fields (NeRF) achieves unprecedented performance in synthesizing novel view synthesis, utilizing multi-view consistency. When capturing multiple inputs, image signal processing (ISP) in modern cameras will independently…

计算机视觉与模式识别 · 计算机科学 2024-08-08 Yuehao Wang , Chaoyi Wang , Bingchen Gong , Tianfan Xue

Recently, 3D Gaussian Splatting has emerged as a prominent research direction owing to its ultrarapid training speed and high-fidelity rendering capabilities. However, the unstructured and irregular nature of Gaussian point clouds poses…

计算机视觉与模式识别 · 计算机科学 2026-02-16 Xiao Ren , Yu Liu , Ning An , Jian Cheng , Xin Qiao , He Kong

High-quality novel view synthesis for large-scale scenes presents a challenging dilemma in 3D computer vision. Existing methods typically partition large scenes into multiple regions, reconstruct a 3D representation using Gaussian splatting…

计算机视觉与模式识别 · 计算机科学 2025-06-11 Xiaohan Zhang , Sitong Wang , Yushen Yan , Yi Yang , Mingda Xu , Qi Liu