中文
相关论文

相关论文: NeRFLiX: High-Quality Neural View Synthesis by Lea…

200 篇论文

Novel view synthesis is a long-standing problem. In this work, we consider a variant of the problem where we are given only a few context views sparsely covering a scene or an object. The goal is to predict novel viewpoints in the scene,…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Jonáš Kulhánek , Erik Derner , Torsten Sattler , Robert Babuška

Neural Radiance Fields (NeRFs) increase reconstruction detail for novel view synthesis and scene reconstruction, with applications ranging from large static scenes to dynamic human motion. However, the increased resolution and model-free…

计算机视觉与模式识别 · 计算机科学 2022-06-27 Abiramy Kuganesan , Shih-yang Su , James J. Little , Helge Rhodin

Recently, Neural Radiance Fields (NeRF) has exhibited significant success in novel view synthesis, surface reconstruction, etc. However, since no physical reflection is considered in its rendering pipeline, NeRF mistakes the reflection in…

计算机视觉与模式识别 · 计算机科学 2023-08-08 Junyi Zeng , Chong Bao , Rui Chen , Zilong Dong , Guofeng Zhang , Hujun Bao , Zhaopeng Cui

The quality of three-dimensional reconstruction is a key factor affecting the effectiveness of its application in areas such as virtual reality (VR) and augmented reality (AR) technologies. Neural Radiance Fields (NeRF) can generate…

计算机视觉与模式识别 · 计算机科学 2023-06-09 Qianqiu Tan , Tao Liu , Yinling Xie , Shuwan Yu , Baohua Zhang

Recent advances in Neural Radiance Fields (NeRFs) treat the problem of novel view synthesis as Sparse Radiance Field (SRF) optimization using sparse voxels for efficient and fast rendering (plenoxels,InstantNGP). In order to leverage…

计算机视觉与模式识别 · 计算机科学 2024-02-26 Abdullah Hamdi , Bernard Ghanem , Matthias Nießner

Existing neural radiance fields (NeRF)-based novel view synthesis methods for large-scale outdoor scenes are mainly built on a single altitude. Moreover, they often require a priori camera shooting height and scene scope, leading to…

计算机视觉与模式识别 · 计算机科学 2024-04-19 Jingfeng Guo , Xiaohan Zhang , Baozhu Zhao , Qi Liu

2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this observation, we propose NeRDi, a single-view NeRF synthesis…

计算机视觉与模式识别 · 计算机科学 2022-12-08 Congyue Deng , Chiyu "Max'' Jiang , Charles R. Qi , Xinchen Yan , Yin Zhou , Leonidas Guibas , Dragomir Anguelov

While neural radiance fields (NeRF) led to a breakthrough in photorealistic novel view synthesis, handling mirroring surfaces still denotes a particular challenge as they introduce severe inconsistencies in the scene representation.…

计算机视觉与模式识别 · 计算机科学 2025-01-09 Leif Van Holland , Michael Weinmann , Jan U. Müller , Patrick Stotko , Reinhard Klein

Panoramic observation using fisheye cameras is significant in virtual reality (VR) and robot perception. However, panoramic images synthesized by traditional methods lack depth information and can only provide three degrees-of-freedom…

机器人学 · 计算机科学 2024-11-05 Dongyu Yan , Guanyu Huang , Fengyu Quan , Haoyao Chen

Neural radiance fields (NeRF) has gained significant attention for its exceptional visual effects. However, most existing NeRF methods reconstruct 3D scenes from RGB images captured by visible light cameras. In practical scenarios like…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Chonghao Zhong , Chao Xu

We present a new neural representation, called Neural Ray (NeuRay), for the novel view synthesis task. Recent works construct radiance fields from image features of input views to render novel view images, which enables the generalization…

计算机视觉与模式识别 · 计算机科学 2022-03-29 Yuan Liu , Sida Peng , Lingjie Liu , Qianqian Wang , Peng Wang , Christian Theobalt , Xiaowei Zhou , Wenping Wang

Neural radiance fields (NeRF) excel at synthesizing new views given multi-view, calibrated images of a static scene. When scenes include distractors, which are not persistent during image capture (moving objects, lighting variations,…

计算机视觉与模式识别 · 计算机科学 2024-07-30 Sara Sabour , Suhani Vora , Daniel Duckworth , Ivan Krasin , David J. Fleet , Andrea Tagliasacchi

We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details, especially in…

计算机视觉与模式识别 · 计算机科学 2023-03-14 Xingyi Li , Chaoyi Hong , Yiran Wang , Zhiguo Cao , Ke Xian , Guosheng Lin

We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF). NeRFs have been shown to be remarkably effective for the task of view synthesis - synthesizing photorealistic novel views of…

计算机视觉与模式识别 · 计算机科学 2021-08-11 Lin Yen-Chen , Pete Florence , Jonathan T. Barron , Alberto Rodriguez , Phillip Isola , Tsung-Yi Lin

Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e., recovering a realistic NeRF at a different time of day from a group of…

计算机视觉与模式识别 · 计算机科学 2022-05-31 Xingyu Chen , Qi Zhang , Xiaoyu Li , Yue Chen , Ying Feng , Xuan Wang , Jue Wang

NeRF (Neural Radiance Fields) has demonstrated tremendous potential in novel view synthesis and 3D reconstruction, but its performance is sensitive to input image quality, which struggles to achieve high-fidelity rendering when provided…

计算机视觉与模式识别 · 计算机科学 2024-04-09 Zhongkai Wu , Ziyu Wan , Jing Zhang , Jing Liao , Dong Xu

Neural Radiance Fields (NeRF) have shown impressive capabilities for photorealistic novel view synthesis when trained on dense inputs. However, when trained on sparse inputs, NeRF typically encounters issues of incorrect density or color…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Yingji Zhong , Lanqing Hong , Zhenguo Li , Dan Xu

We present Non-Rigid Neural Radiance Fields (NR-NeRF), a reconstruction and novel view synthesis approach for general non-rigid dynamic scenes. Our approach takes RGB images of a dynamic scene as input (e.g., from a monocular video…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Edgar Tretschk , Ayush Tewari , Vladislav Golyanik , Michael Zollhöfer , Christoph Lassner , Christian Theobalt

We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and…

计算机视觉与模式识别 · 计算机科学 2023-04-26 Xin Huang , Qi Zhang , Ying Feng , Hongdong Li , Xuan Wang , Qing Wang

Novel view synthesis has recently made significant progress with the advent of Neural Radiance Fields (NeRF). DietNeRF is an extension of NeRF that aims to achieve this task from only a few images by introducing a new loss function for…

计算机视觉与模式识别 · 计算机科学 2023-10-23 Daiju Kanaoka , Motoharu Sonogashira , Hakaru Tamukoh , Yasutomo Kawanishi