English
Related papers

Related papers: L4GM: Large 4D Gaussian Reconstruction Model

200 papers

Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However, images from sparse views only contain very limited 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Chen Yang , Sikuang Li , Jiemin Fang , Ruofan Liang , Lingxi Xie , Xiaopeng Zhang , Wei Shen , Qi Tian

Reconstructing dynamic assets from video data is central to many in computer vision and graphics tasks. Existing 4D reconstruction approaches are limited by category-specific models or slow optimization-based methods. Inspired by the recent…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Remy Sabathier , Niloy J. Mitra , David Novotny

Advances in generative modeling have significantly enhanced digital content creation, extending from 2D images to complex 3D and 4D scenes. Despite substantial progress, producing high-fidelity and temporally consistent dynamic 4D content…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 DongFu Yin , Xiaotian Chen , Fei Richard Yu , Xuanchen Li , Xinhao Zhang

Recent advances in generalizable Gaussian splatting (GS) have enabled feed-forward reconstruction of scenes from tens of input views. Long-LRM notably scales this paradigm to 32 input images at $950\times540$ resolution, achieving 360{\deg}…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Chen Ziwen , Hao Tan , Peng Wang , Zexiang Xu , Li Fuxin

The advancement of 4D (i.e., sequential 3D) generation opens up new possibilities for lifelike experiences in various applications, where users can explore dynamic objects or characters from any viewpoint. Meanwhile, video generative models…

Graphics · Computer Science 2025-04-08 Yikai Wang , Guangce Liu , Xinzhou Wang , Zilong Chen , Jiafang Li , Xin Liang , Fuchun Sun , Jun Zhu

Generating animatable human avatars from a single image is essential for various digital human modeling applications. Existing 3D reconstruction methods often struggle to capture fine details in animatable models, while generative…

Computer Vision and Pattern Recognition · Computer Science 2024-12-04 Lingteng Qiu , Shenhao Zhu , Qi Zuo , Xiaodong Gu , Yuan Dong , Junfei Zhang , Chao Xu , Zhe Li , Weihao Yuan , Liefeng Bo , Guanying Chen , Zilong Dong

This paper aims to address the challenge of reconstructing long volumetric videos from multi-view RGB videos. Recent dynamic view synthesis methods leverage powerful 4D representations, like feature grids or point cloud sequences, to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Zhen Xu , Yinghao Xu , Zhiyuan Yu , Sida Peng , Jiaming Sun , Hujun Bao , Xiaowei Zhou

Recent 4D reconstruction methods have yielded impressive results but rely on sharp videos as supervision. However, motion blur often occurs in videos due to camera shake and object movement, while existing methods render blurry results when…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Renlong Wu , Zhilu Zhang , Mingyang Chen , Zifei Yan , Wangmeng Zuo

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…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yue Wu , Xuanhong Chen , Yufan Wu , Wen Li , Yuxi Lu , Kairui Feng

We present a generalizable feed-forward Gaussian splatting framework for human 3D reconstruction and real-time animation that operates directly on multi-view RGB images and their associated SMPL-X poses. Unlike prior methods that rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Devdoot Chatterjee , Zakaria Laskar , C. V. Jawahar

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…

Computer Vision and Pattern Recognition · Computer Science 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

This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Yongzhen Hu , Yihui Yang , Haotong Lin , Yifan Wang , Junting Dong , Yifu Deng , Xinyu Zhu , Fan Jia , Hujun Bao , Xiaowei Zhou , Sida Peng

In robot-assisted minimally invasive surgery, high-fidelity dynamic endoscopic scene reconstruction and simulation are crucial to enhancing downstream tasks and advancing surgical outcomes. However, existing methods primarily focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Changjing Liu , Yiming Huang , Long Bai , Beilei Cui , Hongliang Ren

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…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Melonie de Almeida , Daniela Ivanova , Tong Shi , John H. Williamson , Paul Henderson

Generating dynamic 3D object from a single-view video is challenging due to the lack of 4D labeled data. An intuitive approach is to extend previous image-to-3D pipelines by transferring off-the-shelf image generation models such as score…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Zijie Pan , Zeyu Yang , Xiatian Zhu , Li Zhang

Learning 4D language fields to enable time-sensitive, open-ended language queries in dynamic scenes is essential for many real-world applications. While LangSplat successfully grounds CLIP features into 3D Gaussian representations,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Wanhua Li , Renping Zhou , Jiawei Zhou , Yingwei Song , Johannes Herter , Minghan Qin , Gao Huang , Hanspeter Pfister

Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Xuanyu Yi , Zike Wu , Qiuhong Shen , Qingshan Xu , Pan Zhou , Joo-Hwee Lim , Shuicheng Yan , Xinchao Wang , Hanwang Zhang

Given the high complexity of directly generating high-dimensional data such as 4D, we present 4DVD, a cascaded video diffusion model that generates 4D content in a decoupled manner. Unlike previous multi-view video methods that directly…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Shuzhou Yang , Xiaodong Cun , Xiaoyu Li , Yaowei Li , Jian Zhang

Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Guanjun Wu , Taoran Yi , Jiemin Fang , Lingxi Xie , Xiaopeng Zhang , Wei Wei , Wenyu Liu , Qi Tian , Xinggang Wang

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…

Graphics · Computer Science 2026-04-08 Denis Rozumny , Jonathon Luiten , Numair Khan , Johannes Schönberger , Peter Kontschieder