中文
相关论文

相关论文: DriveEnv-NeRF: Exploration of A NeRF-Based Autonom…

200 篇论文

Deep learning methods for perception are the cornerstone of many robotic systems. Despite their potential for impressive performance, obtaining real-world training data is expensive, and can be impractically difficult for some tasks.…

机器人学 · 计算机科学 2024-03-08 Nikhil Mishra , Maximilian Sieb , Pieter Abbeel , Xi Chen

Virtual Reality (VR) is becoming ubiquitous with the rise of consumer displays and commercial VR platforms. Such displays require low latency and high quality rendering of synthetic imagery with reduced compute overheads. Recent advances in…

图形学 · 计算机科学 2022-07-25 Nianchen Deng , Zhenyi He , Jiannan Ye , Budmonde Duinkharjav , Praneeth Chakravarthula , Xubo Yang , Qi Sun

In this work, we consider the problem of learning end to end perception to control for ground vehicles solely from aerial imagery. Photogrammetric simulators allow the synthesis of novel views through the transformation of pre-generated…

机器人学 · 计算机科学 2024-10-21 Varun Murali , Guy Rosman , Sertac Karaman , Daniela Rus

Current methods for 3D reconstruction and environmental mapping frequently face challenges in achieving high precision, highlighting the need for practical and effective solutions. In response to this issue, our study introduces FlyNeRF, a…

机器人学 · 计算机科学 2024-04-22 Maria Dronova , Vladislav Cheremnykh , Alexey Kotcov , Aleksey Fedoseev , Dzmitry Tsetserukou

Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering. To speed up the volume rendering process, many acceleration methods have been proposed at the cost of large memory…

计算机视觉与模式识别 · 计算机科学 2022-12-19 Sicheng Li , Hao Li , Yue Wang , Yiyi Liao , Lu Yu

Neural radiance fields (NeRFs) are able to synthesize realistic novel views from multi-view images captured from distinct positions and perspectives. In NeRF's rendering pipeline, neural networks are used to represent a scene independently…

计算机视觉与模式识别 · 计算机科学 2023-06-01 Kang Han , Wei Xiang , Lu Yu

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…

Neural Radiance Fields (NeRFs) implicitly model continuous three-dimensional scenes using a set of images with known camera poses, enabling the rendering of photorealistic novel views. However, existing NeRF-based methods encounter…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Zhengyu Zou , Jingfeng Li , Hao Li , Xiaolei Hou , Jinwen Hu , Jingkun Chen , Lechao Cheng , Dingwen Zhang

We propose a novel visual re-localization method based on direct matching between the implicit 3D descriptors and the 2D image with transformer. A conditional neural radiance field(NeRF) is chosen as the 3D scene representation in our…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Jianlin Liu , Qiang Nie , Yong Liu , Chengjie Wang

High-fidelity sensor simulation of light-based sensors such as cameras and LiDARs is critical for safe and accurate autonomy testing. Neural radiance field (NeRF)-based methods that reconstruct sensor observations via ray-casting of…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Yun Chen , Matthew Haines , Jingkang Wang , Sahil Jain , Krzysztof Baron-Lis , Sivabalan Manivasagam , Ze Yang , Raquel Urtasun

Recently, Neural Radiance Fields (NeRF) has shown promising performances on reconstructing 3D scenes and synthesizing novel views from a sparse set of 2D images. Albeit effective, the performance of NeRF is highly influenced by the quality…

计算机视觉与模式识别 · 计算机科学 2022-09-20 Xuran Pan , Zihang Lai , Shiji Song , Gao Huang

We present an end-to-end system for the high-fidelity capture, model reconstruction, and real-time rendering of walkable spaces in virtual reality using neural radiance fields. To this end, we designed and built a custom multi-camera rig to…

Deep Reinforcement Learning (DRL) has shown remarkable success in solving complex tasks across various research fields. However, transferring DRL agents to the real world is still challenging due to the significant discrepancies between…

机器学习 · 计算机科学 2024-10-22 Dianzhao Li , Ostap Okhrin

Recent efforts in Neural Rendering Fields (NeRF) have shown impressive results on novel view synthesis by utilizing implicit neural representation to represent 3D scenes. Due to the process of volumetric rendering, the inference speed for…

计算机视觉与模式识别 · 计算机科学 2023-06-27 Junli Cao , Huan Wang , Pavlo Chemerys , Vladislav Shakhrai , Ju Hu , Yun Fu , Denys Makoviichuk , Sergey Tulyakov , Jian Ren

Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have enabled their near photo-realistic, free-viewpoint rendering. Although these methods have shown some potential in creating immersive experiences, two drawbacks limit…

计算机视觉与模式识别 · 计算机科学 2024-06-07 Xinhang Liu , Yu-Wing Tai , Chi-Keung Tang , Pedro Miraldo , Suhas Lohit , Moitreya Chatterjee

We present a photo-realistic training and evaluation simulator (Sim4CV) with extensive applications across various fields of computer vision. Built on top of the Unreal Engine, the simulator integrates full featured physics based cars,…

计算机视觉与模式识别 · 计算机科学 2018-03-28 Matthias Müller , Vincent Casser , Jean Lahoud , Neil Smith , Bernard Ghanem

In this work, we propose the use of Neural Radiance Fields (NeRF) as a scene representation for visual localization. Recently, NeRF has been employed to enhance pose regression and scene coordinate regression models by augmenting the…

计算机视觉与模式识别 · 计算机科学 2024-08-22 Qunjie Zhou , Maxim Maximov , Or Litany , Laura Leal-Taixé

Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry and appearance understanding in a fully self-supervised manner. To apply NeRF-based…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Hyeonjun Jeong , Juyeb Shin , Dongsuk Kum

Neural Radiance Field (NeRF) and its variants have exhibited great success on representing 3D scenes and synthesizing photo-realistic novel views. However, they are generally based on the pinhole camera model and assume all-in-focus inputs.…

计算机视觉与模式识别 · 计算机科学 2022-08-02 Zijin Wu , Xingyi Li , Juewen Peng , Hao Lu , Zhiguo Cao , Weicai Zhong

Neural Radiance Fields (NeRFs) aim to synthesize novel views of objects and scenes, given the object-centric camera views with large overlaps. However, we conjugate that this paradigm does not fit the nature of the street views that are…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Ziyang Xie , Junge Zhang , Wenye Li , Feihu Zhang , Li Zhang