中文
相关论文

相关论文: 3D Gaussian Inpainting with Depth-Guided Cross-Vie…

200 篇论文

Gaussian Splatting (GS), a recent technique for converting discrete points into continuous spatial representations, has shown promising results in 3D scene modeling and 2D image super-resolution. In this paper, we explore its untapped…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Hongyu Li , Chaofeng Chen , Xiaoming Li , Guangming Lu

We present SGS-Intrinsic, an indoor inverse rendering framework that works well for sparse-view images. Unlike existing 3D Gaussian Splatting (3DGS) based methods that focus on object-centric reconstruction and fail to work under sparse…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Jiahao Niu , Rongjia Zheng , Wenju Xu , Wei-Shi Zheng , Qing Zhang

3D Gaussian Splatting (3DGS) has recently emerged as a pioneering approach in explicit scene rendering and computer graphics. Unlike traditional neural radiance field (NeRF) methods, which typically rely on implicit, coordinate-based models…

The emergence of 3D Gaussian Splatting (3DGS) has greatly accelerated the rendering speed of novel view synthesis. Unlike neural implicit representations like Neural Radiance Fields (NeRF) that represent a 3D scene with position and…

计算机视觉与模式识别 · 计算机科学 2024-04-16 Tong Wu , Yu-Jie Yuan , Ling-Xiao Zhang , Jie Yang , Yan-Pei Cao , Ling-Qi Yan , Lin Gao

3D Gaussian Splatting (3DGS) has emerged as a preferred choice alongside Neural Radiance Fields (NeRF) in inverse rendering due to its superior rendering speed. Currently, the common approach in 3DGS is to utilize "single-view" mini-batch…

计算机视觉与模式识别 · 计算机科学 2025-06-18 Minhyuk Choi , Injae Kim , Hyunwoo J. Kim

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…

Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. However, these methods struggle in large-scale, unconstrained…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Niluthpol Chowdhury Mithun , Tuan Pham , Qiao Wang , Ben Southall , Kshitij Minhas , Bogdan Matei , Stephan Mandt , Supun Samarasekera , Rakesh Kumar

Accurate geometric surface reconstruction, providing essential environmental information for navigation and manipulation tasks, is critical for enabling robotic self-exploration and interaction. Recently, 3D Gaussian Splatting (3DGS) has…

计算机视觉与模式识别 · 计算机科学 2025-07-17 Tengfei Wang , Xin Wang , Yongmao Hou , Zhaoning Zhang , Yiwei Xu , Zongqian Zhan

The field of novel view synthesis from images has seen rapid advancements with the introduction of Neural Radiance Fields (NeRF) and more recently with 3D Gaussian Splatting. Gaussian Splatting became widely adopted due to its efficiency…

计算机视觉与模式识别 · 计算机科学 2024-11-07 Ruihong Yin , Vladimir Yugay , Yue Li , Sezer Karaoglu , Theo Gevers

Dense 3D representations of the environment have been a long-term goal in the robotics field. While previous Neural Radiance Fields (NeRF) representation have been prevalent for its implicit, coordinate-based model, the recent emergence of…

机器人学 · 计算机科学 2024-12-20 Siting Zhu , Guangming Wang , Xin Kong , Dezhi Kong , Hesheng Wang

Gaze estimation encounters generalization challenges when dealing with out-of-distribution data. To address this problem, recent methods use neural radiance fields (NeRF) to generate augmented data. However, existing methods based on NeRF…

计算机视觉与模式识别 · 计算机科学 2025-07-10 Xiaobao Wei , Peng Chen , Guangyu Li , Ming Lu , Hui Chen , Feng Tian

Novel view synthesis has advanced significantly with the development of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS). However, achieving high quality without compromising real-time rendering remains challenging,…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Zhongpai Gao , Benjamin Planche , Meng Zheng , Anwesa Choudhuri , Terrence Chen , Ziyan Wu

Recent advancements in diffusion and flow models have greatly improved text-based image editing, yet methods that edit images independently often produce geometrically and photometrically inconsistent results across different views of the…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Josef Bengtson , David Nilsson , Dong In Lee , Yaroslava Lochman , Fredrik Kahl

In-the-wild 3D Gaussian Splatting remains challenging due to transient distractors and illumination-induced cross-view appearance inconsistencies. Existing methods mainly rely on image-level masking to suppress unreliable supervision, but…

计算机视觉与模式识别 · 计算机科学 2026-05-18 Yulei Kang , Tianze Zhu , Jian-Fang Hu , Jianhuang Lai , Wei-Shi Zheng

Efficiently synthesizing novel views from sparse inputs while maintaining accuracy remains a critical challenge in 3D reconstruction. While advanced techniques like radiance fields and 3D Gaussian Splatting achieve rendering quality and…

计算机视觉与模式识别 · 计算机科学 2025-01-22 Chenlu Zhan , Yufei Zhang , Yu Lin , Gaoang Wang , Hongwei Wang

We propose a method to enhance 3D Gaussian Splatting (3DGS)~\cite{Kerbl2023}, addressing challenges in initialization, optimization, and density control. Gaussian Splatting is an alternative for rendering realistic images while supporting…

计算机视觉与模式识别 · 计算机科学 2025-07-02 Xingjun Wang , Lianlei Shan

Radiance fields represented by 3D Gaussians excel at synthesizing novel views, offering both high training efficiency and fast rendering. However, with sparse input views, the lack of multi-view consistency constraints results in poorly…

计算机视觉与模式识别 · 计算机科学 2025-08-27 Yuru Xiao , Deming Zhai , Wenbo Zhao , Kui Jiang , Junjun Jiang , Xianming Liu

Three-dimensional reconstruction in scenes with extreme depth variations remains challenging due to inconsistent supervisory signals between near-field and far-field regions. Existing methods fail to simultaneously address inaccurate depth…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Yu Deng , Baozhu Zhao , Junyan Su , Xiaohan Zhang , Qi Liu

This paper presents GS-RoadPatching, an inpainting method for driving scene completion by referring to completely reconstructed regions, which are represented by 3D Gaussian Splatting (3DGS). Unlike existing 3DGS inpainting methods that…

计算机视觉与模式识别 · 计算机科学 2025-09-25 Guo Chen , Jiarun Liu , Sicong Du , Chenming Wu , Deqi Li , Shi-Sheng Huang , Guofeng Zhang , Sheng Yang

The introduction of 3D Gaussian Splatting (3DGS) has advanced novel view synthesis by utilizing Gaussians to represent scenes. Encoding Gaussian point features with anchor embeddings has significantly enhanced the performance of newer 3DGS…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Junyan Su , Baozhu Zhao , Xiaohan Zhang , Qi Liu