English
Related papers

Related papers: STream3R: Scalable Sequential 3D Reconstruction wi…

200 papers

Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Jisu Nam , Jahyeok Koo , Soowon Son , Jaewoo Jung , Honggyu An , Junhwa Hur , Seungryong Kim

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…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Jisang Han , Honggyu An , Jaewoo Jung , Takuya Narihira , Junyoung Seo , Kazumi Fukuda , Chaehyun Kim , Sunghwan Hong , Yuki Mitsufuji , Seungryong Kim

Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Tianye Ding , Yiming Xie , Yiqing Liang , Moitreya Chatterjee , Pedro Miraldo , Huaizu Jiang

Modern visual agents require representations that are general, causal, and physically structured to operate in real-time streaming environments. However, current vision foundation models remain fragmented, specializing narrowly in image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yibin Yan , Jilan Xu , Shangzhe Di , Haoning Wu , Weidi Xie

The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Luoxi Zhang , Pragyan Shrestha , Yu Zhou , Chun Xie , Itaru Kitahara

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…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Chaoyi Zhou , Run Wang , Feng Luo , Mert D. Pesé , Zhiwen Fan , Yiqi Zhong , Siyu Huang

3D scene reconstruction is essential for applications in virtual reality, robotics, and autonomous driving, enabling machines to understand and interact with complex environments. Traditional 3D Gaussian Splatting techniques rely on images…

Graphics · Computer Science 2025-03-04 Changlin Song , Jiaqi Wang , Liyun Zhu , He Weng

Recently, 3D Gaussian Splatting (3DGS) has reshaped the field of photorealistic 3D reconstruction, achieving impressive rendering quality and speed. However, when applied to large-scale street scenes, existing methods suffer from rapidly…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Guangting Zheng , Jiajun Deng , Xiaomeng Chu , Yu Yuan , Houqiang Li , Yanyong Zhang

We study the problem of single-image 3D object reconstruction. Recent works have diverged into two directions: regression-based modeling and generative modeling. Regression methods efficiently infer visible surfaces, but struggle with…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Zixuan Huang , Mark Boss , Aaryaman Vasishta , James M. Rehg , Varun Jampani

Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly when applied beyond the training context length, revealing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Xingyu Chen , Yue Chen , Yuliang Xiu , Andreas Geiger , Anpei Chen

We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. Unlike prior methods requiring per-scene optimization, Edit3r directly predicts…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Jiageng Liu , Weijie Lyu , Xueting Li , Yejie Guo , Ming-Hsuan Yang

In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The…

Computer Vision and Pattern Recognition · Computer Science 2023-06-08 Shihao Wang , Yingfei Liu , Tiancai Wang , Ying Li , Xiangyu Zhang

Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency, and computational efficiency. Motivated by the principles…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Lin-Zhuo Chen , Jian Gao , Yihang Chen , Ka Leong Cheng , Yipengjing Sun , Liangxiao Hu , Nan Xue , Xing Zhu , Yujun Shen , Yao Yao , Yinghao Xu

We present AMB3R, a multi-view feed-forward model for dense 3D reconstruction on a metric-scale that addresses diverse 3D vision tasks. The key idea is to leverage a sparse, yet compact, volumetric scene representation as our backend,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Hengyi Wang , Lourdes Agapito

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…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Yohann Cabon , Lucas Stoffl , Leonid Antsfeld , Gabriela Csurka , Boris Chidlovskii , Jerome Revaud , Vincent Leroy

Reconstructing dynamic 3D scenes (i.e., 4D geometry) from monocular video is an important yet challenging problem. Conventional multiview geometry-based approaches often struggle with dynamic motion, whereas recent learning-based methods…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Jinjie Mai , Wenxuan Zhu , Haozhe Liu , Bing Li , Cheng Zheng , Jürgen Schmidhuber , Bernard Ghanem

The remarkable achievements of both generative models of 2D images and neural field representations for 3D scenes present a compelling opportunity to integrate the strengths of both approaches. In this work, we propose a methodology that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Azmi Haider , Dan Rosenbaum

Building a robust perception module is crucial for visuomotor policy learning. While recent methods incorporate pre-trained 2D foundation models into robotic perception modules to leverage their strong semantic understanding, they struggle…

Robotics · Computer Science 2025-07-14 Wenbo Cui , Chengyang Zhao , Yuhui Chen , Haoran Li , Zhizheng Zhang , Dongbin Zhao , He Wang

3D super-resolution (3DSR) aims to reconstruct high-resolution (HR) 3D scenes from low-resolution (LR) multi-view images. Existing methods rely on dense LR inputs and per-scene optimization, which restricts the high-frequency priors for…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Xiang Feng , Xiangbo Wang , Tieshi Zhong , Chengkai Wang , Yiting Zhao , Tianxiang Xu , Zhenzhong Kuang , Feiwei Qin , Xuefei Yin , Yanming Zhu

We present PAD3R, a method for reconstructing deformable 3D objects from casually captured, unposed monocular videos. Unlike existing approaches, PAD3R handles long video sequences featuring substantial object deformation, large-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Ting-Hsuan Liao , Haowen Liu , Yiran Xu , Songwei Ge , Gengshan Yang , Jia-Bin Huang