English
Related papers

Related papers: GaussianPretrain: A Simple Unified 3D Gaussian Rep…

200 papers

Urban scene reconstruction is crucial for real-world autonomous driving simulators. Although existing methods have achieved photorealistic reconstruction, they mostly focus on pinhole cameras and neglect fisheye cameras. In fact, how to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Yuan Ren , Guile Wu , Runhao Li , Zheyuan Yang , Yibo Liu , Xingxin Chen , Tongtong Cao , Bingbing Liu

Recent advances in novel view synthesis have enabled real-time rendering speeds with high reconstruction accuracy. 3D Gaussian Splatting (3D-GS), a foundational point-based parametric 3D scene representation, models scenes as large sets of…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Alex Hanson , Allen Tu , Vasu Singla , Mayuka Jayawardhana , Matthias Zwicker , Tom Goldstein

Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Boming Zhao , Yuan Li , Ziyu Sun , Lin Zeng , Yujun Shen , Rui Ma , Yinda Zhang , Hujun Bao , Zhaopeng Cui

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…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Hao Lu , Tianshuo Xu , Wenzhao Zheng , Yunpeng Zhang , Wei Zhan , Dalong Du , Masayoshi Tomizuka , Kurt Keutzer , Yingcong Chen

Multi-sensor fusion is crucial for improving the performance and robustness of end-to-end autonomous driving systems. Existing methods predominantly adopt either attention-based flatten fusion or bird's eye view fusion through geometric…

Robotics · Computer Science 2025-10-29 Shuai Liu , Quanmin Liang , Zefeng Li , Boyang Li , Kai Huang

We propose Video Gaussian Masked Autoencoders (Video-GMAE), a self-supervised approach for representation learning that encodes a sequence of images into a set of Gaussian splats moving over time. Representing a video as a set of Gaussians…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Tanish Baranwal , Himanshu Gaurav Singh , Jathushan Rajasegaran , Jitendra Malik

We present a novel approach, termed ADGaussian, for generalizable street scene reconstruction. The proposed method enables high-quality rendering from merely single-view input. Unlike prior Gaussian Splatting methods that primarily focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Qi Song , Chenghong Li , Haotong Lin , Sida Peng , Rui Huang

3D occupancy prediction is important for autonomous driving due to its comprehensive perception of the surroundings. To incorporate sequential inputs, most existing methods fuse representations from previous frames to infer the current 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Sicheng Zuo , Wenzhao Zheng , Yuanhui Huang , Jie Zhou , Jiwen Lu

Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting excels in real-time rendering and static scene reconstructions but…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mustafa Khan , Hamidreza Fazlali , Dhruv Sharma , Tongtong Cao , Dongfeng Bai , Yuan Ren , Bingbing Liu

We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Qijian Tian , Xin Tan , Yuan Xie , Lizhuang Ma

We present a novel animatable 3D Gaussian model for rendering high-fidelity free-view human motions in real time. Compared to existing NeRF-based methods, the model owns better capability in synthesizing high-frequency details without the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Keyang Ye , Tianjia Shao , Kun Zhou

The significant achievements of pre-trained models leveraging large volumes of data in the field of NLP and 2D vision inspire us to explore the potential of extensive data pre-training for 3D perception in autonomous driving. Toward this…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Shumin Wang , Zhuoran Yang , Lidian Wang , Zhipeng Tang , Heng Li , Lehan Pan , Sha Zhang , Jie Peng , Jianmin Ji , Yanyong Zhang

3D Gaussian Splatting (3DGS) is a recent approach for scene rendering. Although primarily designed for view synthesis, its potential for scene understanding tasks remains underexplored. In this work, we conduct a comparative evaluation of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Julia Farganus , Krzysztof Żurawicki , Arkadiusz Gaweł , Weronika Jakubowska , Halina Kwaśnicka

Efficient neural representations for dynamic video scenes are critical for applications ranging from video compression to interactive simulations. Yet, existing methods often face challenges related to high memory usage, lengthy training…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Andrew Bond , Jui-Hsien Wang , Long Mai , Erkut Erdem , Aykut Erdem

Pre-training on large-scale unlabeled datasets contribute to the model achieving powerful performance on 3D vision tasks, especially when annotations are limited. However, existing rendering-based self-supervised frameworks are…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Hao Liu , Minglin Chen , Yanni Ma , Haihong Xiao , Ying He

Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-08-26 Jun Guo , Xiaojian Ma , Yue Fan , Huaping Liu , Qing Li

Latent scene representation plays a significant role in training reinforcement learning (RL) agents. To obtain good latent vectors describing the scenes, recent works incorporate the 3D-aware latent-conditioned NeRF pipeline into scene…

Robotics · Computer Science 2024-09-30 Jiaxu Wang , Ziyi Zhang , Qiang Zhang , Jia Li , Jingkai Sun , Mingyuan Sun , Junhao He , Renjing Xu

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Tae-Kyeong Kim , Xingxin Chen , Guile Wu , Chengjie Huang , Dongfeng Bai , Bingbing Liu

Ensuring the safety of autonomous vehicles necessitates comprehensive simulation of multi-sensor data, encompassing inputs from both cameras and LiDAR sensors, across various dynamic driving scenarios. Neural rendering techniques, which…

3D semantic occupancy prediction aims to obtain 3D fine-grained geometry and semantics of the surrounding scene and is an important task for the robustness of vision-centric autonomous driving. Most existing methods employ dense grids such…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Yuanhui Huang , Wenzhao Zheng , Yunpeng Zhang , Jie Zhou , Jiwen Lu