中文
相关论文

相关论文: PanoSplatt3R: Leveraging Perspective Pretraining f…

200 篇论文

We present PanoPlane, an approach for high-fidelity sparse-view indoor novel view synthesis that reconstructs closed room geometry via panoramic scene completion. Unlike perspective-based methods that generate training views from limited…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Adil Qureshi , Dongki Jung , Jaehoon Choi , Dinesh Manocha

We propose SelfSplat, a novel 3D Gaussian Splatting model designed to perform pose-free and 3D prior-free generalizable 3D reconstruction from unposed multi-view images. These settings are inherently ill-posed due to the lack of…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Gyeongjin Kang , Jisang Yoo , Jihyeon Park , Seungtae Nam , Hyeonsoo Im , Sangheon Shin , Sangpil Kim , Eunbyung Park

This paper addresses metric 3D reconstruction of indoor scenes by exploiting their inherent geometric regularities with compact representations. Using planar 3D primitives - a well-suited representation for man-made environments - we…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Changkun Liu , Bin Tan , Zeran Ke , Shangzhan Zhang , Jiachen Liu , Ming Qian , Nan Xue , Yujun Shen , Tristan Braud

In this paper, we introduce Splatt3R, a pose-free, feed-forward method for in-the-wild 3D reconstruction and novel view synthesis from stereo pairs. Given uncalibrated natural images, Splatt3R can predict 3D Gaussian Splats without…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Brandon Smart , Chuanxia Zheng , Iro Laina , Victor Adrian Prisacariu

Achieving an immersive experience enabling users to explore virtual environments with six degrees of freedom (6DoF) is essential for various applications such as virtual reality (VR). Wide-baseline panoramas are commonly used in these…

计算机视觉与模式识别 · 计算机科学 2023-12-07 Zheng Chen , Yan-Pei Cao , Yuan-Chen Guo , Chen Wang , Ying Shan , Song-Hai Zhang

We present Pow3r, a novel large 3D vision regression model that is highly versatile in the input modalities it accepts. Unlike previous feed-forward models that lack any mechanism to exploit known camera or scene priors at test time, Pow3r…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Wonbong Jang , Philippe Weinzaepfel , Vincent Leroy , Lourdes Agapito , Jerome Revaud

Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs. However, synthesizing novel views from these panoramic images in real time remains a significant…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Zheng Chen , Chenming Wu , Zhelun Shen , Chen Zhao , Weicai Ye , Haocheng Feng , Errui Ding , Song-Hai Zhang

Sparse-view reconstruction models typically require precise camera poses, yet obtaining these parameters from sparse-view images remains challenging. We introduce FreeSplatter, a scalable feed-forward framework that generates high-quality…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Jiale Xu , Shenghua Gao , Ying Shan

This paper presents RoGSplat, a novel approach for synthesizing high-fidelity novel views of unseen human from sparse multi-view images, while requiring no cumbersome per-subject optimization. Unlike previous methods that typically struggle…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Junjin Xiao , Qing Zhang , Yonewei Nie , Lei Zhu , Wei-Shi Zheng

Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel Gaussians and combine Gaussians from all views as the scene…

计算机视觉与模式识别 · 计算机科学 2025-10-20 Jiaxin Guo , Tongfan Guan , Wenzhen Dong , Wenzhao Zheng , Wenting Wang , Yue Wang , Yeung Yam , Yun-Hui Liu

Panoramic imagery offers a full 360{\deg} field of view and is increasingly common in consumer devices. However, it introduces non-pinhole distortions that challenge joint pose estimation and 3D reconstruction. Existing feed-forward models,…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Yijing Guo , Mengjun Chao , Luo Wang , Tianyang Zhao , Haizhao Dai , Yingliang Zhang , Jingyi Yu , Yujiao Shi

Neural rendering has demonstrated remarkable success in high-quality 3D neural reconstruction and novel view synthesis with dense input views and accurate poses. However, applying it to extremely sparse, unposed views in unbounded 360{\deg}…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Chong Bao , Xiyu Zhang , Zehao Yu , Jiale Shi , Guofeng Zhang , Songyou Peng , Zhaopeng Cui

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

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

With the advent of portable 360{\deg} cameras, panorama has gained significant attention in applications like virtual reality (VR), virtual tours, robotics, and autonomous driving. As a result, wide-baseline panorama view synthesis has…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Cheng Zhang , Haofei Xu , Qianyi Wu , Camilo Cruz Gambardella , Dinh Phung , Jianfei Cai

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have advanced 3D reconstruction and novel view synthesis, but remain heavily dependent on accurate camera poses and dense viewpoint coverage. These requirements limit their…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Jiahui Lu , Haihong Xiao , Xueyan Zhao , Wenxiong Kang

Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are available. Although recent efforts alleviate this issue by enhancing multi-view…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Jimin Tang , Wenyuan Zhang , Junsheng Zhou , Zian Huang , Kanle Shi , Shenkun Xu , Yu-Shen Liu , Zhizhong Han

We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from \textit{unposed} sparse multi-view images. Our model, trained exclusively with photometric loss, achieves real-time 3D…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Botao Ye , Sifei Liu , Haofei Xu , Xueting Li , Marc Pollefeys , Ming-Hsuan Yang , Songyou Peng

Recent efforts in Gaussian-Splat-based Novel View Synthesis can achieve photorealistic rendering; however, such capability is limited in sparse-view scenarios due to sparse initialization and over-fitting floaters. Recent progress in depth…

计算机视觉与模式识别 · 计算机科学 2024-11-20 Yutao Tang , Yuxiang Guo , Deming Li , Cheng Peng

In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no ground-truth annotations and no pretrained priors. During training, NAS3R reconstructs 3D…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Ranran Huang , Weixun Luo , Ye Mao , Krystian Mikolajczyk
‹ 上一页 1 2 3 10 下一页 ›