中文
相关论文

相关论文: Camera-Agnostic Pruning of 3D Gaussian Splats via …

200 篇论文

We introduce NoPoSplat, a feed-forward model capable of reconstructing 3D scenes parameterized by 3D Gaussians from \textit{unposed} sparse multi-view images. Our model, trained exclusively with photometric loss, achieves real-time 3D…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Botao Ye , Sifei Liu , Haofei Xu , Xueting Li , Marc Pollefeys , Ming-Hsuan Yang , Songyou Peng

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

Gaussian Splatting (GS) is a popular approach for 3D reconstruction, mostly due to its ability to converge reasonably fast, faithfully represent the scene and render (novel) views in a fast fashion. However, it suffers from large storage…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Anil Armagan , Albert Saà-Garriga , Bruno Manganelli , Kyuwon Kim , M. Kerim Yucel

The recent introduction of 3D Gaussian Splatting (3DGS) has significantly advanced novel view synthesis. Several studies have further improved the rendering quality of 3DGS, yet they still exhibit noticeable visual discrepancies when…

计算机视觉与模式识别 · 计算机科学 2025-11-20 Junseo Koo , Jinseo Jeong , Gunhee Kim

We present VicaSplat, a novel framework for joint 3D Gaussians reconstruction and camera pose estimation from a sequence of unposed video frames, which is a critical yet underexplored task in real-world 3D applications. The core of our…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Zhiqi Li , Chengrui Dong , Yiming Chen , Zhangchi Huang , Peidong Liu

3D Gaussian splatting (3DGS) is a state-of-the-art representation for real-time photorealistic novel-view synthesis, yet a single high-fidelity scene typically occupies hundreds of megabytes to several gigabytes, exceeding the budgets of…

机器学习 · 计算机科学 2026-05-05 Baobing Zhang , Wanxin Sui

Scene reconstruction has emerged as a central challenge in computer vision, with approaches such as Neural Radiance Fields (NeRF) and Gaussian Splatting achieving remarkable progress. While Gaussian Splatting demonstrates strong performance…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Alexander Valverde , Brian Xu , Yuyin Zhou , Meng Xu , Hongyun Wang

Differentiable 3D Gaussian splatting has emerged as an efficient and flexible rendering technique for representing complex scenes from a collection of 2D views and enabling high-quality real-time novel-view synthesis. However, its reliance…

图形学 · 计算机科学 2025-01-16 Meenakshi Krishnan , Liam Fowl , Ramani Duraiswami

Generating synthetic images is a useful method for cheaply obtaining labeled data for training computer vision models. However, obtaining accurate 3D models of relevant objects is necessary, and the resulting images often have a gap in…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Bram Vanherle , Brent Zoomers , Jeroen Put , Frank Van Reeth , Nick Michiels

In this work, we introduce Coca-Splat, a novel approach to addressing the challenges of sparse view pose-free scene reconstruction and novel view synthesis (NVS) by jointly optimizing camera parameters with 3D Gaussians. Inspired by…

计算机视觉与模式识别 · 计算机科学 2025-04-02 Jiamin Wu , Hongyang Li , Xiaoke Jiang , Yuan Yao , Lei Zhang

We introduce a simple yet effective approach for separating transmitted and reflected light. Our key insight is that the powerful novel view synthesis capabilities provided by modern inverse rendering methods (e.g.,~3D Gaussian splatting)…

计算机视觉与模式识别 · 计算机科学 2024-10-04 Mingyang Xie , Haoming Cai , Sachin Shah , Yiran Xu , Brandon Y. Feng , Jia-Bin Huang , Christopher A. Metzler

Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, these approaches are built on a tremendous number of redundant 3D Gaussian…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Tianchen Deng , Chang Nie , Shuhong Liu , Wenhua Wu , Jianfei Yang , Shenghai Yuan , Jiuming Liu , Danwei Wang , Hesheng Wang

Autonomous agents often require accurate methods for detecting and localizing changes in their environment, particularly when observations are captured from unconstrained and inconsistent viewpoints. We propose a novel label-free,…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Chamuditha Jayanga Galappaththige , Jason Lai , Lloyd Windrim , Donald Dansereau , Niko Suenderhauf , Dimity Miller

Generating high-quality 3D content requires models capable of learning robust distributions of complex scenes and the real-world objects within them. Recent Gaussian-based 3D reconstruction techniques have achieved impressive results in…

图像与视频处理 · 电气工程与系统科学 2024-12-16 Kevin Miao , Harsh Agrawal , Qihang Zhang , Federico Semeraro , Marco Cavallo , Jiatao Gu , Alexander Toshev

3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for…

3D Gaussian Splatting (3DGS) enables real-time, photorealistic novel view synthesis, making it a highly attractive representation for model-based video tracking. However, leveraging the differentiability of the 3DGS renderer "in the wild"…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Avigail Cohen Rimon , Amir Mann , Mirela Ben Chen , Or Litany

Recently, 3D Gaussian Splatting (3DGS) has become one of the mainstream methodologies for novel view synthesis (NVS) due to its high quality and fast rendering speed. However, as a point-based scene representation, 3DGS potentially…

计算机视觉与模式识别 · 计算机科学 2024-05-30 Zhaoliang Zhang , Tianchen Song , Yongjae Lee , Li Yang , Cheng Peng , Rama Chellappa , Deliang Fan

While 3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and real-time rendering, the high memory consumption due to the use of millions of Gaussians limits its practicality. To mitigate this issue,…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Yifei Liu , Zhihang Zhong , Yifan Zhan , Sheng Xu , Xiao Sun

3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in 3D reconstruction, achieving high-quality results with real-time radiance field rendering. However, a key challenge is the substantial storage cost: reconstructing a…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Haishan Wang , Mohammad Hassan Vali , Arno Solin

The recent success of 3D Gaussian Splatting (3DGS) has reshaped novel view synthesis by enabling fast optimization and real-time rendering of high-quality radiance fields. However, it relies on simplified, order-dependent alpha blending and…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Jan U. Müller , Robin Tim Landsgesell , Leif Van Holland , Patrick Stotko , Reinhard Klein