English
Related papers

Related papers: Improving 2D Feature Representations by 3D-Aware F…

200 papers

Precisely perceiving the geometric and semantic properties of real-world 3D objects is crucial for the continued evolution of augmented reality and robotic applications. To this end, we present Foundation Model Embedded Gaussian Splatting…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Xingxing Zuo , Pouya Samangouei , Yunwen Zhou , Yan Di , Mingyang Li

The evolution of 3D visual content calls for innovative methods for modelling shapes based on their intended usage, function and role in a complex scenario. Even if different attempts have been done in this direction, shape modelling still…

Graphics · Computer Science 2022-08-05 Andreas Scalas

We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to obtain an accurate and robust 3D semantic Gaussian Splatting. The 2D features extracted…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Zaiyan Yang , Xinpeng Liu , Heng Guo , Jinglei Shi , Zhanyu Ma , Fumio Okura

We introduce an image upscaling technique tailored for 3D Gaussian Splatting (3DGS) on lightweight GPUs. Compared to 3DGS, it achieves significantly higher rendering speeds and reduces artifacts commonly observed in 3DGS reconstructions.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-18 Simon Niedermayr , Christoph Neuhauser Rüdiger Westermann

With the emergence of Gaussian Splats, recent efforts have focused on large-scale scene geometric reconstruction. However, most of these efforts either concentrate on memory reduction or spatial space division, neglecting information in the…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Butian Xiong , Xiaoyu Ye , Tze Ho Elden Tse , Kai Han , Shuguang Cui , Zhen Li

Semantic segmentation on point clouds is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only features insufficient to distinguish objects with…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Hojun Song , Chae-yeong Song , Jeong-hun Hong , Chaewon Moon , Dong-hwi Kim , Gahyeon Kim , Soo Ye Kim , Yiyi Liao , Jaehyup Lee , Sang-hyo Park

Recent developments in 3D Gaussian Splatting have made significant advances in surface reconstruction. However, scaling these methods to large-scale scenes remains challenging due to high computational demands and the complex dynamic…

Graphics · Computer Science 2025-06-24 Shihan Chen , Zhaojin Li , Zeyu Chen , Qingsong Yan , Gaoyang Shen , Ran Duan

This paper investigates a 2D to 3D image translation method with a straightforward technique, enabling correlated 2D X-ray to 3D CT-like reconstruction. We observe that existing approaches, which integrate information across multiple 2D…

Computer Vision and Pattern Recognition · Computer Science 2024-06-27 Abril Corona-Figueroa , Hubert P. H. Shum , Chris G. Willcocks

Neural Radiance Fields and 3D Gaussian Splatting have advanced novel view synthesis, yet still rely on dense inputs and often degrade at extrapolated views. Recent approaches leverage generative models, such as diffusion models, to provide…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Hongyu Zhou , Zisen Shao , Sheng Miao , Pan Wang , Dongfeng Bai , Bingbing Liu , Yiyi Liao

3D geometric information is essential for manipulation tasks, as robots need to perceive the 3D environment, reason about spatial relationships, and interact with intricate spatial configurations. Recent research has increasingly focused on…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Yueru Jia , Jiaming Liu , Sixiang Chen , Chenyang Gu , Zhilue Wang , Longzan Luo , Lily Lee , Pengwei Wang , Zhongyuan Wang , Renrui Zhang , Shanghang Zhang

Recent advancements in foundation models for 2D vision have substantially improved the analysis of dynamic scenes from monocular videos. However, despite their strong generalization capabilities, these models often lack 3D consistency, a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Haoran Zhou , Gim Hee Lee

As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion. However, fusion-based approaches require…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Xu Yan , Jiantao Gao , Chaoda Zheng , Chao Zheng , Ruimao Zhang , Shenghui Cui , Zhen Li

In this work, we propose a geometry-aware semi-supervised framework for fine-grained building function recognition, utilizing geometric relationships among multi-source data to enhance pseudo-label accuracy in semi-supervised learning,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Weijia Li , Jinhua Yu , Dairong Chen , Yi Lin , Runmin Dong , Xiang Zhang , Conghui He , Haohuan Fu

Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Rui Song , Chenwei Liang , Yan Xia , Walter Zimmer , Hu Cao , Holger Caesar , Andreas Festag , Alois Knoll

Semantic segmentation has emerged as a pivotal area of study in computer vision, offering profound implications for scene understanding and elevating human-machine interactions across various domains. While 2D semantic segmentation has…

Computer Vision and Pattern Recognition · Computer Science 2024-07-24 Aditya Krishnan , Jayneel Vora , Prasant Mohapatra

We present an approach that combines appearance and semantic information for 2D image-based localization (2D-VL) across large perceptual changes and time lags. Compared to appearance features, the semantic layout of a scene is generally…

Computer Vision and Pattern Recognition · Computer Science 2019-07-04 Zachary Seymour , Karan Sikka , Han-Pang Chiu , Supun Samarasekera , Rakesh Kumar

GAN-based image editing task aims at manipulating image attributes in the latent space of generative models. Most of the previous 2D and 3D-aware approaches mainly focus on editing attributes in images with ambiguous semantics or regions…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Zhijun Zhai , Zengmao Wang , Xiaoxiao Long , Kaixuan Zhou , Bo Du

3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. Although many approaches have been proposed and achieved impressive performance, they all require dense object-sentence pair…

Computer Vision and Pattern Recognition · Computer Science 2023-07-19 Zehan Wang , Haifeng Huang , Yang Zhao , Linjun Li , Xize Cheng , Yichen Zhu , Aoxiong Yin , Zhou Zhao

3D Gaussian Splatting (3DGS) has begun incorporating rich information from 2D foundation models. However, most approaches rely on a bottom-up optimization process that treats raw 2D features as ground truth, incurring increased…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Hyunjoon Lee , Joonkyu Min , Jaesik Park

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Siming Yan , Chen Song , Youkang Kong , Qixing Huang