中文
相关论文

相关论文: DrivingForward: Feed-forward 3D Gaussian Splatting…

200 篇论文

Fast and flexible 3D scene reconstruction from unstructured image collections remains a significant challenge. We present YoNoSplat, a feedforward model that reconstructs high-quality 3D Gaussian Splatting representations from an arbitrary…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Botao Ye , Boqi Chen , Haofei Xu , Daniel Barath , Marc Pollefeys

Recent feed-forward Gaussian reconstruction models adopt a pixel-aligned formulation that maps each 2D pixel to a 3D Gaussian, entangling Gaussian representations tightly with the input images. In this paper, we propose AnchorSplat, a novel…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Xiaoxue Zhang , Xiaoxu Zheng , Yixuan Yin , Tiao Zhao , Kaihua Tang , Michael Bi Mi , Zhan Xu , Dave Zhenyu Chen

Accurate 3D reconstruction of vehicles is vital for applications such as vehicle inspection, predictive maintenance, and urban planning. Existing methods like Neural Radiance Fields and Gaussian Splatting have shown impressive results but…

计算机视觉与模式识别 · 计算机科学 2025-07-17 Davide Di Nucci , Matteo Tomei , Guido Borghi , Luca Ciuffreda , Roberto Vezzani , Rita Cucchiara

Reconstructing large-scale urban scenes from sparse aerial views is a crucial yet challenging task. Due to biased top-down and shallow-oblique camera poses, sparse aerial captures exhibit strong evidence imbalance: roofs and open regions…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Dongli Wu , Zhuoxiao Li , Tongyan Hua , Yinrui Ren , Xiaobao Wei , Rongjun Qin , Wufan Zhao

We present TokenSplat, a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation from unposed multi-view images. At its core, TokenSplat introduces a Token-aligned Gaussian Prediction module that aligns…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Yihui Li , Chengxin Lv , Zichen Tang , Hongyu Yang , Di Huang

We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by satellite. Faithful reconstructions require good camera coverage, but ground imagery is…

Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation. Although recent methods achieve high-fidelity reconstructions, they either rely on costly human annotations for object…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Carl Lindström , Mahan Rafidashti , Maryam Fatemi , Lars Hammarstrand , Martin R. Oswald , Lennart Svensson

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

Feedforward Gaussian Splatting has recently emerged as an efficient paradigm for 4D reconstruction in autonomous driving. However, in unstructured off-road scenes, its performance degrades due to high-frequency geometry, ego-motion jitter,…

计算机视觉与模式识别 · 计算机科学 2026-05-07 Shuo Wang , Jilin Mei , Fuyang Liu , Wenfei Guan , Fanjie Kong , Zhihua Zhao , Shuai Wang , Chen Min , Yu Hu

We present LangFlash, a feed-forward framework for 3D Language Gaussian Splatting that reconstructs 3D scenes parameterized by Gaussian primitives enriched with language-aligned semantic features from sparse unposed multi-view images.…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Yilong Liu , Wanhua Li , Chen Zhu-Tian , Hanspeter Pfister

Feed-forward 3D reconstruction for autonomous driving has advanced rapidly, yet existing methods struggle with the joint challenges of sparse, non-overlapping camera views and complex scene dynamics. We present UniSplat, a general…

计算机视觉与模式识别 · 计算机科学 2025-11-07 Chen Shi , Shaoshuai Shi , Xiaoyang Lyu , Chunyang Liu , Kehua Sheng , Bo Zhang , Li Jiang

3D Gaussian Splatting (3DGS) has emerged as a revolutionary 3D representation. However, its substantial data size poses a major barrier to widespread adoption. While feed-forward 3DGS compression offers a practical alternative to costly…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Zhening Liu , Rui Song , Yushi Huang , Yingdong Hu , Xinjie Zhang , Jiawei Shao , Zehong Lin , Jun Zhang

Sparse-view reconstruction models typically require precise camera poses, yet obtaining these parameters from sparse-view images remains challenging. We introduce FreeSplatter, a scalable feed-forward framework that generates high-quality…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Jiale Xu , Shenghua Gao , Ying Shan

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Peizhen Zheng , Dongjing Jiang , Qingchong Jiao , Redouane EL Bouchtaoui , Flynnwell Jianfei Zhang

Urban scene reconstruction is crucial for real-world autonomous driving simulators. Although existing methods have achieved photorealistic reconstruction, they mostly focus on pinhole cameras and neglect fisheye cameras. In fact, how to…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Yuan Ren , Guile Wu , Runhao Li , Zheyuan Yang , Yibo Liu , Xingxin Chen , Tongtong Cao , Bingbing Liu

We investigate data augmentation for 3D object detection in autonomous driving. We utilize recent advancements in 3D reconstruction based on Gaussian Splatting for 3D object placement in driving scenes. Unlike existing diffusion-based…

计算机视觉与模式识别 · 计算机科学 2025-04-24 Farhad G. Zanjani , Davide Abati , Auke Wiggers , Dimitris Kalatzis , Jens Petersen , Hong Cai , Amirhossein Habibian

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential for multi-view surface reconstruction. Existing methods employ optimization-based…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Chensheng Dai , Shengjun Zhang , Min Chen , Yueqi Duan

In this work, we revisit several key design choices of modern Transformer-based approaches for feed-forward 3D Gaussian Splatting (3DGS) prediction. We argue that the common practice of regressing Gaussian means as depths along camera rays…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Jiawei Ren , Michal Jan Tyszkiewicz , Jiahui Huang , Zan Gojcic

Incrementally recovering real-sized 3D geometry from a pose-free RGB stream is a challenging task in 3D reconstruction, requiring minimal assumptions on input data. Existing methods can be broadly categorized into end-to-end and visual…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Linqing Zhao , Xiuwei Xu , Yirui Wang , Hao Wang , Wenzhao Zheng , Yansong Tang , Haibin Yan , Jiwen Lu

Feed-forward 3D Gaussian Splatting (3DGS) models enable real-time scene generation but are hindered by suboptimal pixel-aligned primitive placement, which relies on a dense, rigid grid that limits both quality and efficiency. We introduce a…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Arthur Moreau , Richard Shaw , Michal Nazarczuk , Jisu Shin , Thomas Tanay , Zhensong Zhang , Songcen Xu , Eduardo Pérez-Pellitero