中文
相关论文

相关论文: Pay Attention to Where You Looked

200 篇论文

Novel View Synthesis (NVS) has traditionally relied on models with explicit 3D inductive biases combined with known camera parameters from Structure-from-Motion (SfM) beforehand. Recent vision foundation models like VGGT take an orthogonal…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Youming Deng , Songyou Peng , Junyi Zhang , Kathryn Heal , Tiancheng Sun , John Flynn , Steve Marschner , Lucy Chai

Learning to generate natural scenes has always been a daunting task in computer vision. This is even more laborious when generating images with very different views. When the views are very different, the view fields have little overlap or…

计算机视觉与模式识别 · 计算机科学 2020-07-21 Hao Ding , Songsong Wu , Hao Tang , Fei Wu , Guangwei Gao , Xiao-Yuan Jing

In this paper, we propose the first generalizable view synthesis approach that specifically targets multi-view stereo-camera images. Since recent stereo matching has demonstrated accurate geometry prediction, we introduce stereo matching…

计算机视觉与模式识别 · 计算机科学 2024-04-23 Haechan Lee , Wonjoon Jin , Seung-Hwan Baek , Sunghyun Cho

Novel View Synthesis (NVS) is the task of generating new images of a scene from viewpoints that were not part of the original input. Diffusion-based NVS can generate high-quality, temporally consistent images, however, remains…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Yuchen Xia , Souvik Kundu , Mosharaf Chowdhury , Nishil Talati

Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Qi Zhang , Yunfei Gong , Daijie Chen , Antoni B. Chan , Hui Huang

Currently almost all state-of-the-art novel view synthesis and reconstruction models rely on calibrated cameras or additional geometric priors for training. These prerequisites significantly limit their applicability to massive uncalibrated…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Ruoyu Wang , Yi Ma , Shenghua Gao

Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at…

计算机视觉与模式识别 · 计算机科学 2021-12-16 Pierluigi Zama Ramirez , Diego Martin Arroyo , Alessio Tonioni , Federico Tombari

Recent photorealistic Novel View Synthesis (NVS) advances have increasingly gained attention. However, these approaches remain constrained to small indoor scenes. While optimization-based NVS models have attempted to address this,…

计算机视觉与模式识别 · 计算机科学 2025-01-14 Aditya Rauniyar , Omar Alama , Silong Yong , Katia Sycara , Sebastian Scherer

Neural view synthesis (NVS) is one of the most successful techniques for synthesizing free viewpoint videos, capable of achieving high fidelity from only a sparse set of captured images. This success has led to many variants of the…

计算机视觉与模式识别 · 计算机科学 2023-10-25 Hanxue Liang , Tianhao Wu , Param Hanji , Francesco Banterle , Hongyun Gao , Rafal Mantiuk , Cengiz Oztireli

We introduce a method for novel view synthesis given only a single wide-baseline stereo image pair. In this challenging regime, 3D scene points are regularly observed only once, requiring prior-based reconstruction of scene geometry and…

计算机视觉与模式识别 · 计算机科学 2023-04-18 Yilun Du , Cameron Smith , Ayush Tewari , Vincent Sitzmann

3D Gaussian Splatting has recently emerged as a powerful tool for fast and accurate novel-view synthesis from a set of posed input images. However, like most novel-view synthesis approaches, it relies on accurate camera pose information,…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Christian Schmidt , Jens Piekenbrinck , Bastian Leibe

Neural Radiance Fields (NeRF) have recently demonstrated photo-realistic results for the task of novel view synthesis. In this paper, we propose to apply novel view synthesis to the robot relocalization problem: we demonstrate improvement…

计算机视觉与模式识别 · 计算机科学 2021-10-14 Arthur Moreau , Nathan Piasco , Dzmitry Tsishkou , Bogdan Stanciulescu , Arnaud de La Fortelle

We present a method for generating consistent novel views from a single source image. Our approach focuses on maximizing the reuse of visible pixels from the source image. To achieve this, we use a monocular depth estimator that transfers…

计算机视觉与模式识别 · 计算机科学 2023-10-26 Yash Kant , Aliaksandr Siarohin , Michael Vasilkovsky , Riza Alp Guler , Jian Ren , Sergey Tulyakov , Igor Gilitschenski

High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques. The rendered HDR images capture a wider range of brightness levels containing more details of the…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Yuanhao Cai , Zihao Xiao , Yixun Liang , Minghan Qin , Yulun Zhang , Xiaokang Yang , Yaoyao Liu , Alan Yuille

Large transformer-based models have made significant progress in generalizable novel view synthesis (NVS) from sparse input views, generating novel viewpoints without the need for test-time optimization. However, these models are…

Novel view synthesis for dynamic $3$D scenes poses a significant challenge. Many notable efforts use NeRF-based approaches to address this task and yield impressive results. However, these methods rely heavily on sufficient motion parallax…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Huiqiang Sun , Xingyi Li , Juewen Peng , Liao Shen , Zhiguo Cao , Ke Xian , Guosheng Lin

Novel view synthesis in 360$^\circ$ scenes from extremely sparse input views is essential for applications like virtual reality and augmented reality. This paper presents a novel framework for novel view synthesis in extremely sparse-view…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Guangan Chen , Anh Minh Truong , Hanhe Lin , Michiel Vlaminck , Wilfried Philips , Hiep Luong

Gaussian Splatting (GS) has significantly elevated scene reconstruction efficiency and novel view synthesis (NVS) accuracy compared to Neural Radiance Fields (NeRF), particularly for dynamic scenes. However, current 4D NVS methods, whether…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Fang Li , Hao Zhang , Narendra Ahuja

Novel view synthesis from images, for example, with 3D Gaussian splatting, has made great progress. Rendering fidelity and speed are now ready even for demanding virtual reality applications. However, the problem of assisting humans in…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Ayaka Yasunaga , Hideo Saito , Dieter Schmalstieg , Shohei Mori

We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Min-Seop Kwak , Junho Kim , Sangdoo Yun , Dongyoon Han , Taekyung Kim , Seungryong Kim , Jin-Hwa Kim