中文
相关论文

相关论文: Feed-Forward Bullet-Time Reconstruction of Dynamic…

200 篇论文

Transforming casually captured, monocular videos into fully immersive dynamic experiences is a highly ill-posed task, and comes with significant challenges, e.g., reconstructing unseen regions, and dealing with the ambiguity in monocular…

图形学 · 计算机科学 2026-04-08 Denis Rozumny , Jonathon Luiten , Numair Khan , Johannes Schönberger , Peter Kontschieder

Emerging video diffusion models achieve high visual fidelity but fundamentally couple scene dynamics with camera motion, limiting their ability to provide precise spatial and temporal control. We introduce a 4D-controllable video diffusion…

计算机视觉与模式识别 · 计算机科学 2025-12-05 Yiming Wang , Qihang Zhang , Shengqu Cai , Tong Wu , Jan Ackermann , Zhengfei Kuang , Yang Zheng , Frano Rajič , Siyu Tang , Gordon Wetzstein

Feedforward reconstruction is crucial for autonomous driving applications, where rapid scene reconstruction enables efficient utilization of large-scale driving datasets in closed-loop simulation and other downstream tasks, eliminating the…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Zhongrui Yu , Zhao Wang , Yijia Xie , Yida Wang , Xueyang Zhang , Yifei Zhan , Kun Zhan

Bullet time is a type of visual effect commonly used in film, television and games that makes time seem to slow down or stop while still preserving dynamic details in the scene. It usually requires multiple sets of cameras to move slowly…

计算机视觉与模式识别 · 计算机科学 2023-04-04 Linquan Yu , Yan Gao , Yangtian Yan , Wentao Zeng

Dynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present Instant4D, a monocular…

计算机视觉与模式识别 · 计算机科学 2025-10-02 Zhanpeng Luo , Haoxi Ran , Li Lu

We propose Flash3D, a method for scene reconstruction and novel view synthesis from a single image which is both very generalisable and efficient. For generalisability, we start from a "foundation" model for monocular depth estimation and…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Stanislaw Szymanowicz , Eldar Insafutdinov , Chuanxia Zheng , Dylan Campbell , João F. Henriques , Christian Rupprecht , Andrea Vedaldi

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…

图形学 · 计算机科学 2025-03-04 Changlin Song , Jiaqi Wang , Liyun Zhu , He Weng

Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Qianqian Wang , Vickie Ye , Hang Gao , Weijia Zeng , Jake Austin , Zhengqi Li , Angjoo Kanazawa

We present a method for fast 3D reconstruction and real-time rendering of dynamic humans from monocular videos with accompanying parametric body fits. Our method can reconstruct a dynamic human in less than 3h using a single GPU, compared…

计算机视觉与模式识别 · 计算机科学 2023-03-22 Ignacio Rocco , Iurii Makarov , Filippos Kokkinos , David Novotny , Benjamin Graham , Natalia Neverova , Andrea Vedaldi

Generating ``bullet-time'' effects of human free-viewpoint videos is critical for immersive visual effects and VR/AR experience. Recent neural advances still lack the controllable and interactive bullet-time design ability for human…

计算机视觉与模式识别 · 计算机科学 2021-08-13 Liao Wang , Ziyu Wang , Pei Lin , Yuheng Jiang , Xin Suo , Minye Wu , Lan Xu , Jingyi Yu

Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is particularly challenging in dynamic…

机器人学 · 计算机科学 2025-12-09 Xingguang Zhong , Liren Jin , Marija Popović , Jens Behley , Cyrill Stachniss

We introduce a novel method for dynamic free-view synthesis of an ambient scenes from a monocular capture bringing a immersive quality to the viewing experience. Our method builds upon the recent advancements in 3D Gaussian Splatting (3DGS)…

计算机视觉与模式识别 · 计算机科学 2024-06-14 Meng-Li Shih , Jia-Bin Huang , Changil Kim , Rajvi Shah , Johannes Kopf , Chen Gao

We present a real-time monocular dense SLAM system designed bottom-up from MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system is robust on in-the-wild video sequences despite making no…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Riku Murai , Eric Dexheimer , Andrew J. Davison

Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view…

We present a method to perform novel view and time synthesis of dynamic scenes, requiring only a monocular video with known camera poses as input. To do this, we introduce Neural Scene Flow Fields, a new representation that models the…

计算机视觉与模式识别 · 计算机科学 2021-04-22 Zhengqi Li , Simon Niklaus , Noah Snavely , Oliver Wang

We propose a method for generating a temporally remapped video that matches the desired target duration while maximally preserving natural video dynamics. Our approach trains a neural network through self-supervision to recognize and…

计算机视觉与模式识别 · 计算机科学 2022-05-12 Simon Jenni , Markus Woodson , Fabian Caba Heilbron

Reconstructing dynamic humans together with static scenes from monocular videos remains difficult, especially under fast motion, where RGB frames suffer from motion blur. Event cameras exhibit distinct advantages, e.g., microsecond temporal…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Xiaoting Yin , Hao Shi , Kailun Yang , Jiajun Zhai , Shangwei Guo , Lin Wang , Kaiwei Wang

We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene. Our work builds upon recent advances in neural implicit representation and uses continuous and…

计算机视觉与模式识别 · 计算机科学 2021-05-14 Chen Gao , Ayush Saraf , Johannes Kopf , Jia-Bin Huang

We present MoVieS, a Motion-aware View Synthesis model that reconstructs 4D dynamic scenes from monocular videos in one second. It represents dynamic 3D scenes with pixel-aligned Gaussian primitives and explicitly supervises their…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Chenguo Lin , Yuchen Lin , Panwang Pan , Yifan Yu , Tao Hu , Honglei Yan , Katerina Fragkiadaki , Yadong Mu

Reconstructing dynamic 4D scenes remains challenging due to the presence of moving objects that corrupt camera pose estimation. Existing optimization methods alleviate this issue with additional supervision, but they are mostly…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Juntong Fang , Zequn Chen , Weiqi Zhang , Donglin Di , Xuancheng Zhang , Chengmin Yang , Yu-Shen Liu
‹ 上一页 1 2 3 10 下一页 ›