中文
相关论文

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

200 篇论文

We present Point2Pose, a model-free method for causal 6D pose tracking of multiple rigid objects from monocular RGB-D video. Initialized only from sparse image points on the objects to be tracked, our approach tracks multiple unseen objects…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Tzu-Yuan Lin , Ho Jae Lee , Kevin Doherty , Yonghyeon Lee , Sangbae Kim

Recent progress in 3D/4D scene generation emphasizes the importance of physical alignment throughout video generation and scene reconstruction. However, existing methods improve the alignment separately at each stage, making it difficult to…

计算机视觉与模式识别 · 计算机科学 2025-07-31 Byeongjun Park , Hyojun Go , Hyelin Nam , Byung-Hoon Kim , Hyungjin Chung , Changick Kim

We present Free-Range Gaussians, a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images. This is done through flow matching over Gaussian parameters. Our generative formulation…

Recent advances in Dense Simultaneous Localization and Mapping (SLAM) have demonstrated remarkable performance in static environments. However, dense SLAM in dynamic environments remains challenging. Most methods directly remove dynamic…

机器人学 · 计算机科学 2025-12-11 Siting Zhu , Yuxiang Huang , Wenhua Wu , Chaokang Jiang , Yongbo Chen , I-Ming Chen , Hesheng Wang

Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities since their data association usually relies on feature correspondences. Additionally, learning-based SLAM systems often fall short in terms of real-time…

计算机视觉与模式识别 · 计算机科学 2024-08-22 Zhongche Qu , Zhi Zhang , Cong Liu , Jianhua Yin

With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption. Although various compression techniques have been proposed,…

计算机视觉与模式识别 · 计算机科学 2025-03-13 Yihang Chen , Qianyi Wu , Mengyao Li , Weiyao Lin , Mehrtash Harandi , Jianfei Cai

Generalizable 3D Gaussian Splatting has recently emerged as an efficient approach for novel-view synthesis, enabling feed-forward synthesis from only a few input views. However, existing pixel-wise feed-forward methods suffer from…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Hoang Chuong Nguyen , Renjie Wu , Jose M. Alvarez , Miaomiao Liu

Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map for autonomous agents and safety-critical applications,…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Chamuditha Jayanga Galappaththige , Thomas Gottwald , Peter Stehr , Edgar Heinert , Niko Suenderhauf , Dimity Miller , Matthias Rottmann

Six degree of freedom (6DoF) pose estimation for novel objects is a critical task in computer vision, yet it faces significant challenges in high-speed and low-light scenarios where standard RGB cameras suffer from motion blur. While event…

计算机视觉与模式识别 · 计算机科学 2026-01-05 Huiming Yang , Linglin Liao , Fei Ding , Sibo Wang , Zijian Zeng

4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality of details. In this paper, we introduce DreamGaussian4D…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Jiawei Ren , Liang Pan , Jiaxiang Tang , Chi Zhang , Ang Cao , Gang Zeng , Ziwei Liu

Recently, the integration of the efficient feed-forward scheme into 3D Gaussian Splatting (3DGS) has been actively explored. However, most existing methods focus on sparse view reconstruction of small regions and cannot produce eligible…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Yunsong Wang , Tianxin Huang , Hanlin Chen , Gim Hee Lee

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

A major breakthrough in 3D reconstruction is the feedforward paradigm to generate pixel-wise 3D points or Gaussian primitives from sparse, unposed images. To further incorporate semantics while avoiding the significant memory and storage…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Yu Sheng , Jiajun Deng , Xinran Zhang , Yu Zhang , Bei Hua , Yanyong Zhang , Jianmin Ji

Reconstructing dynamic 3D scenes with photorealistic detail and strong temporal coherence remains a significant challenge. Existing Gaussian splatting approaches for dynamic scene modeling often rely on per-frame optimization, which can…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Tingxuan Huang , Haowei Zhu , Jun-hai Yong , Hao Pan , Bin Wang

Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed. While the recent 3D Gaussian Splatting works well on small-scale and object-centric scenes, scaling it up to large…

计算机视觉与模式识别 · 计算机科学 2024-02-28 Jiaqi Lin , Zhihao Li , Xiao Tang , Jianzhuang Liu , Shiyong Liu , Jiayue Liu , Yangdi Lu , Xiaofei Wu , Songcen Xu , Youliang Yan , Wenming Yang

3D neural style transfer has gained significant attention for its potential to provide user-friendly stylization with spatial consistency. However, existing 3D style transfer methods often fall short in terms of inference efficiency,…

计算机视觉与模式识别 · 计算机科学 2024-10-15 Wanlin Liang , Hongbin Xu , Weitao Chen , Feng Xiao , Wenxiong Kang

We present Gaussian See, Gaussian Do, a novel approach for semantic 3D motion transfer from multiview video. Our method enables rig-free, cross-category motion transfer between objects with semantically meaningful correspondence. Building…

计算机视觉与模式识别 · 计算机科学 2025-11-20 Yarin Bekor , Gal Michael Harari , Or Perel , Or Litany

Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging due to the difficulty of capturing accurate deformations while maintaining computational efficiency. We propose SCas4D, a cascaded optimization…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Jipeng Lyu , Jiahua Dong , Yu-Xiong Wang

Over the past year, 3D Gaussian Splatting (3DGS) has received significant attention for its ability to represent 3D scenes in a perceptually accurate manner. However, it can require a substantial amount of storage since each splat's…

计算机视觉与模式识别 · 计算机科学 2025-04-11 Brent Zoomers , Maarten Wijnants , Ivan Molenaers , Joni Vanherck , Jeroen Put , Lode Jorissen , Nick Michiels

Learning neural implicit surfaces from volume rendering has become popular for multi-view reconstruction. Neural surface reconstruction approaches can recover complex 3D geometry that are difficult for classical Multi-view Stereo (MVS)…

计算机视觉与模式识别 · 计算机科学 2023-12-27 Mohamed Shawky Sabae , Hoda Anis Baraka , Mayada Mansour Hadhoud