中文
相关论文

相关论文: Fast3R: Towards 3D Reconstruction of 1000+ Images …

200 篇论文

DUSt3R introduced a novel paradigm in geometric computer vision by proposing a model that can provide dense and unconstrained Stereo 3D Reconstruction of arbitrary image collections with no prior information about camera calibration nor…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Yohann Cabon , Lucas Stoffl , Leonid Antsfeld , Gabriela Csurka , Boris Chidlovskii , Jerome Revaud , Vincent Leroy

Multi-view 3D reconstruction has remained an essential yet challenging problem in the field of computer vision. While DUSt3R and its successors have achieved breakthroughs in 3D reconstruction from unposed images, these methods exhibit…

图像与视频处理 · 电气工程与系统科学 2025-09-16 Sidun Liu , Wenyu Li , Peng Qiao , Yong Dou

Image matching is a key component of modern 3D vision algorithms, essential for accurate scene reconstruction and localization. MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Jingxing Li , Yongjae Lee , Abhay Kumar Yadav , Cheng Peng , Rama Chellappa , Deliang Fan

Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision. Yet despite matching being fundamentally a 3D problem, intrinsically linked to camera pose and scene geometry, it is typically treated as a 2D…

计算机视觉与模式识别 · 计算机科学 2024-06-17 Vincent Leroy , Yohann Cabon , Jérôme Revaud

3D reconstruction, which aims to recover the dense three-dimensional structure of a scene, is a cornerstone technology for numerous applications, including augmented/virtual reality, autonomous driving, and robotics. While traditional…

计算机视觉与模式识别 · 计算机科学 2025-07-14 Wei Zhang , Yihang Wu , Songhua Li , Wenjie Ma , Xin Ma , Qiang Li , Qi Wang

Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera parameters e.g. intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain, yet they are mandatory to triangulate…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Shuzhe Wang , Vincent Leroy , Yohann Cabon , Boris Chidlovskii , Jerome Revaud

Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Vivek Alumootil , Tuan-Anh Vu

Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches treat these capabilities in isolation, leading to redundant pipelines and compounded…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Chaoyi Zhou , Run Wang , Feng Luo , Mert D. Pesé , Zhiwen Fan , Yiqi Zhong , Siyu Huang

Reconstructing and semantically interpreting 3D scenes from sparse 2D views remains a fundamental challenge in computer vision. Conventional methods often decouple semantic understanding from reconstruction or necessitate costly per-scene…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Xiangyu Sun , Haoyi Jiang , Liu Liu , Seungtae Nam , Gyeongjin Kang , Xinjie Wang , Wei Sui , Zhizhong Su , Wenyu Liu , Xinggang Wang , Eunbyung Park

Current multi-view 3D reconstruction methods rely on accurate camera calibration and pose estimation, requiring complex and time-intensive pre-processing that hinders their practical deployment. To address this challenge, we introduce…

图形学 · 计算机科学 2025-08-07 Haodong Zhu , Changbai Li , Yangyang Ren , Zichao Feng , Xuhui Liu , Hanlin Chen , Xiantong Zhen , Baochang Zhang

We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global…

计算机视觉与模式识别 · 计算机科学 2025-08-15 Yushi Lan , Yihang Luo , Fangzhou Hong , Shangchen Zhou , Honghua Chen , Zhaoyang Lyu , Shuai Yang , Bo Dai , Chen Change Loy , Xingang Pan

Image stitching aim to align two images taken from different viewpoints into one seamless, wider image. However, when the 3D scene contains depth variations and the camera baseline is significant, noticeable parallax occurs-meaning the…

计算机视觉与模式识别 · 计算机科学 2025-12-25 Muhua Zhu , Xinhao Jin , Chengbo Wang , Yongcong Zhang , Yifei Xue , Tie Ji , Yizhen Lao

We present Spann3R, a novel approach for dense 3D reconstruction from ordered or unordered image collections. Built on the DUSt3R paradigm, Spann3R uses a transformer-based architecture to directly regress pointmaps from images without any…

计算机视觉与模式识别 · 计算机科学 2024-08-30 Hengyi Wang , Lourdes Agapito

Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Zhenggang Tang , Yuchen Fan , Dilin Wang , Hongyu Xu , Rakesh Ranjan , Alexander Schwing , Zhicheng Yan

Panoptic segmentation of 3D scenes, involving the segmentation and classification of object instances in a dense 3D reconstruction of a scene, is a challenging problem, especially when relying solely on unposed 2D images. Existing…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Lojze Zust , Yohann Cabon , Juliette Marrie , Leonid Antsfeld , Boris Chidlovskii , Jerome Revaud , Gabriela Csurka

Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved realistic reconstructions on large scenes, but optimize per…

计算机视觉与模式识别 · 计算机科学 2024-10-01 Yun Chen , Jingkang Wang , Ze Yang , Sivabalan Manivasagam , Raquel Urtasun

Room layout estimation from multiple-perspective images is poorly investigated due to the complexities that emerge from multi-view geometry, which requires muti-step solutions such as camera intrinsic and extrinsic estimation, image…

计算机视觉与模式识别 · 计算机科学 2025-03-05 Yaxuan Huang , Xili Dai , Jianan Wang , Xianbiao Qi , Yixing Yuan , Xiangyu Yue

Despite significant progress in 3D avatar reconstruction, it still faces challenges such as high time complexity, sensitivity to data quality, and low data utilization. We propose FastAvatar, a feedforward 3D avatar framework capable of…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Yue Wu , Xuanhong Chen , Yufan Wu , Wen Li , Yuxi Lu , Kairui Feng

We present PreF3R, Pose-Free Feed-forward 3D Reconstruction from an image sequence of variable length. Unlike previous approaches, PreF3R removes the need for camera calibration and reconstructs the 3D Gaussian field within a canonical…

计算机视觉与模式识别 · 计算机科学 2024-11-27 Zequn Chen , Jiezhi Yang , Heng Yang

In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DUSt3R, that are originally designed for static 3D scene…

计算机视觉与模式识别 · 计算机科学 2025-11-03 Jisang Han , Honggyu An , Jaewoo Jung , Takuya Narihira , Junyoung Seo , Kazumi Fukuda , Chaehyun Kim , Sunghwan Hong , Yuki Mitsufuji , Seungryong Kim
‹ 上一页 1 2 3 10 下一页 ›