中文
相关论文

相关论文: ConFixGS: Learning to Fix Feedforward 3D Gaussian …

200 篇论文

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

Recent developments in 3D Gaussian Splatting have significantly enhanced novel view synthesis, yet generating high-quality renderings from extreme novel viewpoints or partially observed regions remains challenging. Meanwhile, diffusion…

计算机视觉与模式识别 · 计算机科学 2025-08-21 Jiaxin Wei , Stefan Leutenegger , Simon Schaefer

Recently, 3D Gaussian Splatting (3DGS) has demonstrated remarkable success in 3D reconstruction and novel view synthesis. However, reconstructing 3D scenes from sparse viewpoints remains highly challenging due to insufficient visual…

计算机视觉与模式识别 · 计算机科学 2025-09-24 Zhaorui Wang , Yi Gu , Deming Zhou , Renjing Xu

Reconstructing 3D scenes using 3D Gaussian Splatting (3DGS) from sparse views is an ill-posed problem due to insufficient information, often resulting in noticeable artifacts. While recent approaches have sought to leverage generative…

计算机视觉与模式识别 · 计算机科学 2025-08-14 Xingyilang Yin , Qi Zhang , Jiahao Chang , Ying Feng , Qingnan Fan , Xi Yang , Chi-Man Pun , Huaqi Zhang , Xiaodong Cun

Feed-forward 3D reconstruction offers substantial runtime advantages over per-scene optimization, which remains slow at inference and often fragile under sparse views. However, existing feed-forward methods still have potential for further…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Tianyu Chen , Wei Xiang , Kang Han , Yu Lu , Di Wu , Gaowen Liu , Ramana Rao Kompella

High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their per-pixel Gaussian prediction paradigm often suffers from…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Cheng Chi , Xianqi Wang , Hongcheng Luo , Mingfei Tu , Gangwei Xu , Zehan Zhang , Bing Wang , Guang Chen , Hangjun Ye , Sida Peng , Xin Yang , Haiyang Sun

Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric cases. In…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Yuanhao Cai , He Zhang , Kai Zhang , Yixun Liang , Mengwei Ren , Fujun Luan , Qing Liu , Soo Ye Kim , Jianming Zhang , Zhifei Zhang , Yuqian Zhou , Yulun Zhang , Xiaokang Yang , Zhe Lin , Alan Yuille

A single-pass driving clip frequently results in incomplete scanning of the road structure, making reconstructed scene expanding a critical requirement for sensor simulators to effectively regress driving actions. Although contemporary 3D…

计算机视觉与模式识别 · 计算机科学 2025-07-28 Sicong Du , Jiarun Liu , Qifeng Chen , Hao-Xiang Chen , Tai-Jiang Mu , Sheng Yang

We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Qijian Tian , Xin Tan , Yuan Xie , Lizhuang Ma

Neural Radiance Fields and 3D Gaussian Splatting have advanced novel view synthesis, yet still rely on dense inputs and often degrade at extrapolated views. Recent approaches leverage generative models, such as diffusion models, to provide…

计算机视觉与模式识别 · 计算机科学 2026-01-29 Hongyu Zhou , Zisen Shao , Sheng Miao , Pan Wang , Dongfeng Bai , Bingbing Liu , Yiyi Liao

Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Riccardo de Lutio , Tobias Fischer , Yen-Yu Chang , Yuxuan Zhang , Jay Zhangjie Wu , Xuanchi Ren , Tianchang Shen , Katarina Tothova , Zan Gojcic , Haithem Turki

3D Gaussian Splatting (3DGS) revolutionized novel view rendering. Instead of inferring from dense spatial points, as implicit representations do, 3DGS uses sparse Gaussians. This enables real-time performance but increases space…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Cem Eteke , Enzo Tartaglione

Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Anran Wu , Long Peng , Xin Di , Xueyuan Dai , Chen Wu , Yang Wang , Xueyang Fu , Yang Cao , Zheng-Jun Zha

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Jiaqi Yao , Zhongmiao Yan , Jingyi Xu , Songpengcheng Xia , Yan Xiang , Ling Pei

Recent advancements in 3D editing have highlighted the potential of text-driven methods in real-time, user-friendly AR/VR applications. However, current methods rely on 2D diffusion models without adequately considering multi-view…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Dong In Lee , Hyeongcheol Park , Jiyoung Seo , Eunbyung Park , Hyunje Park , Ha Dam Baek , Sangheon Shin , Sangmin Kim , Sangpil Kim

Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large scale variations. Existing methods either refine renderings…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Sirshapan Mitra , Yogesh S. Rawat

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

We aim to address sparse-view reconstruction of a 3D scene by leveraging priors from large-scale vision models. While recent advancements such as 3D Gaussian Splatting (3DGS) have demonstrated remarkable successes in 3D reconstruction,…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Hanyang Yu , Xiaoxiao Long , Ping Tan

Neural scene representations, such as 3D Gaussian Splatting (3DGS), have enabled high-quality neural rendering; however, their large storage and transmission costs hinder deployment in resource-constrained environments. Existing compression…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Jiaqi Chen , Xinhao Ji , Yuanyuan Gao , Hao Li , Yuning Gong , Yifei Liu , Dan Xu , Zhihang Zhong , Dingwen Zhang , Xiao Sun

Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Xi Liu , Chaoyi Zhou , Siyu Huang
‹ 上一页 1 2 3 10 下一页 ›