中文
相关论文

相关论文: Non-Rigid Neural Radiance Fields: Reconstruction a…

200 篇论文

We propose a Transformer-based NeRF (TransNeRF) to learn a generic neural radiance field conditioned on observed-view images for the novel view synthesis task. By contrast, existing MLP-based NeRFs are not able to directly receive observed…

计算机视觉与模式识别 · 计算机科学 2022-06-14 Dan Wang , Xinrui Cui , Septimiu Salcudean , Z. Jane Wang

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

This paper presents a neural rendering method for controllable portrait video synthesis. Recent advances in volumetric neural rendering, such as neural radiance fields (NeRF), has enabled the photorealistic novel view synthesis of static…

计算机视觉与模式识别 · 计算机科学 2021-08-12 ShahRukh Athar , Zhixin Shu , Dimitris Samaras

Neural Radiance Field (NeRF) has broken new ground in the novel view synthesis due to its simple concept and state-of-the-art quality. However, it suffers from severe performance degradation unless trained with a dense set of images with…

计算机视觉与模式识别 · 计算机科学 2023-04-13 Seunghyeon Seo , Donghoon Han , Yeonjin Chang , Nojun Kwak

Neural implicit representation of visual scenes has attracted a lot of attention in recent research of computer vision and graphics. Most prior methods focus on how to reconstruct 3D scene representation from a set of images. In this work,…

计算机视觉与模式识别 · 计算机科学 2024-09-12 Wenpu Li , Pian Wan , Peng Wang , Jinghang Li , Yi Zhou , Peidong Liu

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images,…

计算机视觉与模式识别 · 计算机科学 2021-08-25 Anpei Chen , Zexiang Xu , Fuqiang Zhao , Xiaoshuai Zhang , Fanbo Xiang , Jingyi Yu , Hao Su

We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields involves optimizing the representation…

计算机视觉与模式识别 · 计算机科学 2021-06-01 Alex Yu , Vickie Ye , Matthew Tancik , Angjoo Kanazawa

Neural Radiance Fields (NeRF) have shown remarkable performance in neural rendering-based novel view synthesis. However, NeRF suffers from severe visual quality degradation when the input images have been captured under imperfect…

计算机视觉与模式识别 · 计算机科学 2024-01-02 Byeonghyeon Lee , Howoong Lee , Usman Ali , Eunbyung Park

Volumetric neural rendering methods, such as neural radiance fields (NeRFs), have enabled photo-realistic novel view synthesis. However, in their standard form, NeRFs do not support the editing of objects, such as a human head, within a…

计算机视觉与模式识别 · 计算机科学 2022-06-15 ShahRukh Athar , Zexiang Xu , Kalyan Sunkavalli , Eli Shechtman , Zhixin Shu

Novel view synthesis (NVS) is a challenge in computer vision and graphics, focusing on generating realistic images of a scene from unobserved camera poses, given a limited set of authentic input images. Neural radiance fields (NeRF)…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Austin Peng

We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on Neural Radiance Fields (NeRF), which uses the weights of a multilayer perceptron…

计算机视觉与模式识别 · 计算机科学 2021-01-07 Ricardo Martin-Brualla , Noha Radwan , Mehdi S. M. Sajjadi , Jonathan T. Barron , Alexey Dosovitskiy , Daniel Duckworth

Recently, the editing of neural radiance fields (NeRFs) has gained considerable attention, but most prior works focus on static scenes while research on the appearance editing of dynamic scenes is relatively lacking. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Shangzan Zhang , Sida Peng , Yinji ShenTu , Qing Shuai , Tianrun Chen , Kaicheng Yu , Hujun Bao , Xiaowei Zhou

Endoscopy is essential in medical imaging, used for diagnosis, prognosis and treatment. Developing a robust dynamic 3D reconstruction pipeline for endoscopic videos could enhance visualization, improve diagnostic accuracy, aid in treatment…

计算机视觉与模式识别 · 计算机科学 2026-02-18 Laura Salort-Benejam , Antonio Agudo

Volumetric reconstruction of dynamic scenes is an important problem in computer vision. It is especially challenging in poor lighting and with fast motion. This is partly due to limitations of RGB cameras: To capture frames under low…

计算机视觉与模式识别 · 计算机科学 2025-07-18 Viktor Rudnev , Gereon Fox , Mohamed Elgharib , Christian Theobalt , Vladislav Golyanik

We propose Neural-DynamicReconstruction (NDR), a template-free method to recover high-fidelity geometry and motions of a dynamic scene from a monocular RGB-D camera. In NDR, we adopt the neural implicit function for surface representation…

计算机视觉与模式识别 · 计算机科学 2022-10-17 Hongrui Cai , Wanquan Feng , Xuetao Feng , Yan Wang , Juyong Zhang

Neural Radiance Fields (NeRFs) have demonstrated prominent performance in novel view synthesis. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Min Wang , Xin Huang , Guoqing Zhou , Qifeng Guo , Qing Wang

We present a method for learning 3D geometry and physics parameters of a dynamic scene from only a monocular RGB video input. To decouple the learning of underlying scene geometry from dynamic motion, we represent the scene as a…

计算机视觉与模式识别 · 计算机科学 2022-10-25 Yi-Ling Qiao , Alexander Gao , Ming C. Lin

We present CG-NeRF, a cascade and generalizable neural radiance fields method for view synthesis. Recent generalizing view synthesis methods can render high-quality novel views using a set of nearby input views. However, the rendering speed…

计算机视觉与模式识别 · 计算机科学 2023-11-22 Phong Nguyen-Ha , Lam Huynh , Esa Rahtu , Jiri Matas , Janne Heikkila

Neural Radiance Fields (NeRF) have transformed novel view synthesis by modeling scene-specific volumetric representations directly from images. While generalizable NeRF models can generate novel views across unknown scenes by learning…

计算机视觉与模式识别 · 计算机科学 2025-05-27 You Wang , Li Fang , Hao Zhu , Fei Hu , Long Ye , Zhan Ma

Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene. However, images photographed from a low-light scene can hardly be used to train a NeRF…

计算机视觉与模式识别 · 计算机科学 2023-07-21 Haoyuan Wang , Xiaogang Xu , Ke Xu , Rynson WH. Lau