中文
相关论文

相关论文: No Pose, No Problem in 4D: Feed-Forward Dynamic Ga…

200 篇论文

Novel view synthesis from a sparse set of input images is a challenging problem of great practical interest, especially when camera poses are absent or inaccurate. Direct optimization of camera poses and usage of estimated depths in neural…

计算机视觉与模式识别 · 计算机科学 2024-06-12 Kaiwen Jiang , Yang Fu , Mukund Varma T , Yash Belhe , Xiaolong Wang , Hao Su , Ravi Ramamoorthi

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

We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image. Our approach unifies the generative priors of video diffusion models with geometry and motion constraints learned from…

计算机视觉与模式识别 · 计算机科学 2026-04-08 Panwang Pan , Chenguo Lin , Jingjing Zhao , Chenxin Li , Yuchen Lin , Haopeng Li , Honglei Yan , Kairun Wen , Yunlong Lin , Yixuan Yuan , Yadong Mu

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…

计算机视觉与模式识别 · 计算机科学 2025-12-04 Haoran Zhou , Gim Hee Lee

This paper tackles the challenge of recovering 4D dynamic scenes from videos captured by as few as four portable cameras. Learning to model scene dynamics for temporally consistent novel-view rendering is a foundational task in computer…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Junsheng Zhou , Zhifan Yang , Liang Han , Wenyuan Zhang , Kanle Shi , Shenkun Xu , Yu-Shen Liu

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

Recent advances in 3D Gaussian Splatting have shown promising results. Existing methods typically assume static scenes and/or multiple images with prior poses. Dynamics, sparse views, and unknown poses significantly increase the problem…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Weihang Li , Weirong Chen , Shenhan Qian , Jiajie Chen , Daniel Cremers , Haoang Li

3D Gaussian Splatting, known for enabling high-quality static scene reconstruction with fast rendering, is increasingly being applied to multi-view dynamic scene reconstruction. A common strategy involves learning a deformation field to…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Han Jiao , Jiakai Sun , Yexing Xu , Lei Zhao , Wei Xing , Huaizhong Lin

Free-Viewpoint Video (FVV) enables immersive 3D experiences, but efficient compression of dynamic 3D representation remains a major challenge. Existing dynamic 3D Gaussian Splatting methods couple reconstruction with optimization-dependent…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Wenkang Zhang , Yan Zhao , Qiang Wang , Zhixin Xu , Li Song , Zhengxue Cheng

Online novel view synthesis remains challenging, requiring robust scene reconstruction from sequential, often unposed, observations. We present ReCoSplat, an autoregressive feed-forward Gaussian Splatting model supporting posed or unposed…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Freeman Cheng , Botao Ye , Xueting Li , Junqi You , Fangneng Zhan , Ming-Hsuan Yang

High-fidelity visual reconstruction and novel-view synthesis are essential for realistic closed-loop evaluation in autonomous driving. While 4D Gaussian Splatting (4DGS) offers a promising balance of accuracy and efficiency, existing…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Haibao Yu , Kuntao Xiao , Jiahang Wang , Ruiyang Hao , Yuxin Huang , Guoran Hu , Haifang Qin , Bowen Jing , Yuntian Bo , Ping Luo

Sparse-view 3D Gaussian splatting seeks to render high-quality novel views of 3D scenes from a limited set of input images. While recent pose-free feed-forward methods leveraging pre-trained 3D priors have achieved impressive results, most…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Muyu Xu , Fangneng Zhan , Xiaoqin Zhang , Ling Shao , Shijian Lu

Simultaneously localizing camera poses and constructing Gaussian radiance fields in dynamic scenes establish a crucial bridge between 2D images and the 4D real world. Instead of removing dynamic objects as distractors and reconstructing…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Yanyan Li , Youxu Fang , Zunjie Zhu , Kunyi Li , Yong Ding , Federico Tombari

In this work, we introduce a generative approach for pose-free (without camera parameters) reconstruction of 360 scenes from a sparse set of 2D images. Pose-free scene reconstruction from incomplete, pose-free observations is usually…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Soumava Paul , Prakhar Kaushik , Alan Yuille

Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. While recent differentiable rendering methods such as Neural…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Jingkang Wang , Henry Che , Yun Chen , Ze Yang , Lily Goli , Sivabalan Manivasagam , Raquel Urtasun

Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance significantly degrades in dynamic environments. This…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Ying Zang , Xuanyi Liu , Yidong Han , Deyi Ji , Chaotao Ding , Yuanqi Hu , Qi Zhu , Xuanfu Li , Jin Ma , Lingyun Sun , Tianrun Chen , Lanyun Zhu

Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Seungjun Oh , Younggeun Lee , Hyejin Jeon , Eunbyung Park

Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Melonie de Almeida , Daniela Ivanova , Tong Shi , John H. Williamson , Paul Henderson

LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift,…

计算机视觉与模式识别 · 计算机科学 2025-08-20 Chin-Yang Lin , Cheng Sun , Fu-En Yang , Min-Hung Chen , Yen-Yu Lin , Yu-Lun Liu

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