中文
相关论文

相关论文: Rethinking Open-Vocabulary Segmentation of Radianc…

200 篇论文

We present a novel approach to perform 3D semantic segmentation solely from 2D supervision by leveraging Neural Radiance Fields (NeRFs). By extracting features along a surface point cloud, we achieve a compact representation of the scene…

计算机视觉与模式识别 · 计算机科学 2023-10-10 Dominik Hollidt , Clinton Wang , Polina Golland , Marc Pollefeys

Understanding 3D scenes is a crucial challenge in computer vision research with applications spanning multiple domains. Recent advancements in distilling 2D vision-language foundation models into neural fields, like NeRF and 3DGS, enable…

计算机视觉与模式识别 · 计算机科学 2024-12-20 Zihan Gao , Lingling Li , Licheng Jiao , Fang Liu , Xu Liu , Wenping Ma , Yuwei Guo , Shuyuan Yang

Radiance Fields have become a powerful tool for modeling 3D scenes from multiple images. However, they remain difficult to segment into semantically meaningful regions. Some methods work well using 2D semantic masks, but they generalize…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Corentin Dumery , Aoxiang Fan , Ren Li , Nicolas Talabot , Pascal Fua

3D semantic segmentation provides high-level scene understanding for applications in robotics, autonomous systems, \textit{etc}. Traditional methods adapt exclusively to either task-specific goals (open-vocabulary segmentation) or scene…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Doriand Petit , Steve Bourgeois , Vincent Gay-Bellile , Florian Chabot , Loïc Barthe

This review thoroughly examines the role of semantically-aware Neural Radiance Fields (NeRFs) in visual scene understanding, covering an analysis of over 250 scholarly papers. It explores how NeRFs adeptly infer 3D representations for both…

计算机视觉与模式识别 · 计算机科学 2024-02-20 Thang-Anh-Quan Nguyen , Amine Bourki , Mátyás Macudzinski , Anthony Brunel , Mohammed Bennamoun

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…

计算机视觉与模式识别 · 计算机科学 2024-08-26 Jun Guo , Xiaojian Ma , Yue Fan , Huaping Liu , Qing Li

In this paper, we address the challenge of decomposing Neural Radiance Fields (NeRF) into objects from an open vocabulary, a critical task for object manipulation in 3D reconstruction and view synthesis. Current techniques for NeRF…

计算机视觉与模式识别 · 计算机科学 2023-10-26 Hao Zhang , Fang Li , Narendra Ahuja

To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence. Given different types of visual inputs such as…

计算机视觉与模式识别 · 计算机科学 2020-10-20 Bo Yang

Accurate 3D scene representation and panoptic understanding are essential for applications such as virtual reality, robotics, and autonomous driving. However, challenges persist with existing methods, including precise 2D-to-3D mapping,…

计算机视觉与模式识别 · 计算机科学 2024-10-08 Shenghao Li

Neural Radiance Fields (NeRFs) have emerged as a popular approach for novel view synthesis. While NeRFs are quickly being adapted for a wider set of applications, intuitively editing NeRF scenes is still an open challenge. One important…

Neural Radiance Fields or NeRFs have become the representation of choice for problems in view synthesis or image-based rendering, as well as in many other applications across computer graphics and vision, and beyond. At their core, NeRFs…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Ravi Ramamoorthi

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…

机器人学 · 计算机科学 2024-09-30 Jiaxu Wang , Ziyi Zhang , Qiang Zhang , Jia Li , Jingkai Sun , Mingyuan Sun , Junhao He , Renjing Xu

Emerging neural radiance fields (NeRF) are a promising scene representation for computer graphics, enabling high-quality 3D reconstruction and novel view synthesis from image observations. However, editing a scene represented by a NeRF is…

计算机视觉与模式识别 · 计算机科学 2022-10-18 Sosuke Kobayashi , Eiichi Matsumoto , Vincent Sitzmann

With the introduction of Neural Radiance Fields (NeRFs), novel view synthesis has recently made a big leap forward. At the core, NeRF proposes that each 3D point can emit radiance, allowing to conduct view synthesis using differentiable…

计算机视觉与模式识别 · 计算机科学 2023-03-17 Marie-Julie Rakotosaona , Fabian Manhardt , Diego Martin Arroyo , Michael Niemeyer , Abhijit Kundu , Federico Tombari

The development of Neural Radiance Fields (NeRFs) has provided a potent representation for encapsulating the geometric and appearance characteristics of 3D scenes. Enhancing the capabilities of NeRFs in open-vocabulary 3D semantic…

计算机视觉与模式识别 · 计算机科学 2024-09-24 Guibiao Liao , Kaichen Zhou , Zhenyu Bao , Kanglin Liu , Qing Li

Neural Radiance Fields (NeRFs) have remodeled 3D scene representation since release. NeRFs can effectively reconstruct complex 3D scenes from 2D images, advancing different fields and applications such as scene understanding, 3D content…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Wenhui Xiao , Remi Chierchia , Rodrigo Santa Cruz , Xuesong Li , David Ahmedt-Aristizabal , Olivier Salvado , Clinton Fookes , Leo Lebrat

Image translation and manipulation have gain increasing attention along with the rapid development of deep generative models. Although existing approaches have brought impressive results, they mainly operated in 2D space. In light of recent…

计算机视觉与模式识别 · 计算机科学 2023-04-04 Yuedong Chen , Qianyi Wu , Chuanxia Zheng , Tat-Jen Cham , Jianfei Cai

Comprehending 3D environments is vital for intelligent systems in domains like robotics and autonomous navigation. Voxel grids offer a structured representation of 3D space, but extracting high-level semantic meaning remains challenging.…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Alan Dao , Norapat Buppodom

Neural Radiance Fields (NeRF) have been widely adopted for reconstructing high quality 3D point clouds from 2D RGB images. However, the segmentation of these reconstructed 3D scenes is more essential for downstream tasks such as object…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Jiangsan Zhao , Jakob Geipel , Krzysztof Kusnierek , Xuean Cui

Methods have recently been proposed that densely segment 3D volumes into classes using only color images and expert supervision in the form of sparse semantically annotated pixels. While impressive, these methods still require a relatively…

计算机视觉与模式识别 · 计算机科学 2022-09-27 Kenneth Blomqvist , Lionel Ott , Jen Jen Chung , Roland Siegwart
‹ 上一页 1 2 3 10 下一页 ›