English
Related papers

Related papers: FLARE: Feed-forward Geometry, Appearance and Camer…

200 papers

Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on accurate camera pose priors. Existing approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Qingsong Yan , Qiang Wang , Kaiyong Zhao , Jie Chen , Bo Li , Xiaowen Chu , Fei Deng

Sparse-view 3D reconstruction is essential for applications in which dense image acquisition is impractical, such as robotics, augmented/virtual reality (AR/VR), and autonomous systems. In these settings, minimal image overlap prevents…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Tanveer Younis , Zhanglin Cheng

Synthesizing novel view images from a few views is a challenging but practical problem. Existing methods often struggle with producing high-quality results or necessitate per-object optimization in such few-view settings due to the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Paul Yoo , Jiaxian Guo , Yutaka Matsuo , Shixiang Shane Gu

Automated 3D scene generation is pivotal for applications spanning virtual reality, digital content creation, and Embodied AI. While computer graphics prioritizes aesthetic layouts, vision and robotics demand scenes that mirror real-world…

Graphics · Computer Science 2026-03-31 Minzhang Li , Kuixiang Shao , Xuebing Li , Yuyang Jiao , Yinuo Bai , Hengan Zhou , Sixian Shen , Jiayuan Gu , Jingyi Yu

We present a methodology to model articulated objects using a sparse set of images with unknown poses. Current methods require dense multi-view observations and ground-truth camera poses. Our approach operates with as few as four views per…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Jianning Deng , Kartic Subr , Hakan Bilen

Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, task-specific feedforward models. We introduce UFO-4D, a unified feedforward framework to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Junhwa Hur , Charles Herrmann , Songyou Peng , Philipp Henzler , Zeyu Ma , Todd Zickler , Deqing Sun

The development of large-scale 3D scene reconstruction and novel view synthesis methods mostly rely on datasets comprising perspective images with narrow fields of view (FoV). While effective for small-scale scenes, these datasets require…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Ulas Gunes , Matias Turkulainen , Xuqian Ren , Arno Solin , Juho Kannala , Esa Rahtu

Fixed-length fingerprint representations, which map each fingerprint to a compact and fixed-size feature vector, are computationally efficient and well-suited for large-scale matching. However, designing a robust representation that…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Zhiyu Pan , Xiongjun Guan , Yongjie Duan , Jianjiang Feng , Jie Zhou

We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images. Due to the large variations in body shapes, poses, and cloth types, existing methods mostly require hours of…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Rong Wang , Fabian Prada , Ziyan Wang , Zhongshi Jiang , Chengxiang Yin , Junxuan Li , Shunsuke Saito , Igor Santesteban , Javier Romero , Rohan Joshi , Hongdong Li , Jason Saragih , Yaser Sheikh

Feed-forward 3D reconstruction methods aim to predict the 3D structure of a scene directly from input images, providing a faster alternative to per-scene optimization approaches. Significant progress has been made in single-view and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Sam Bahrami , Dylan Campbell

We introduce SPFSplatV2, an efficient feed-forward framework for 3D Gaussian splatting from sparse multi-view images, requiring no ground-truth poses during training and inference. It employs a shared feature extraction backbone, enabling…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Ranran Huang , Krystian Mikolajczyk

Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to ground free-form language queries in 3D Gaussian fields. However, existing methods rely on single-view pseudo supervision, leading to viewpoint drift and inconsistent predictions…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Yuwen Tao , Kanglei Zhou , Xin Tan , Yuan Xie

2D Gaussian splatting provides an efficient explicit representation for image reconstruction, but existing methods still require costly per-image iterative optimization or rely on handcrafted priors for primitive allocation. We present AIR,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Zhaojie Zeng , Yuesong Wang , Yawei Luo , Tao Guan

Estimating the 6D pose of objects unseen during training is highly desirable yet challenging. Zero-shot object 6D pose estimation methods address this challenge by leveraging additional task-specific supervision provided by large-scale,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-09 Andrea Caraffa , Davide Boscaini , Amir Hamza , Fabio Poiesi

We propose a feed-forward method for dense Signed Distance Field (SDF) regression from unstructured image collections in less than three seconds, without camera calibration or post-hoc fusion. Our key insight is that the intermediate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Laura Fink , Linus Franke , George Kopanas , Marc Stamminger , Peter Hedman

LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode. Under adverse conditions, degradation or failure of the camera sensor can…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Rohit Mohan , Florian Drews , Yakov Miron , Daniele Cattaneo , Abhinav Valada

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Botao Ye , Sifei Liu , Haofei Xu , Xueting Li , Marc Pollefeys , Ming-Hsuan Yang , Songyou Peng

For nonlinear multispectral computed tomography (CT), accurate and fast image reconstruction is challenging when the scanning geometries under different X-ray energy spectra are inconsistent or mismatched. Motivated by this, we propose an…

Numerical Analysis · Mathematics 2025-07-28 Yu Gao , Chong Chen

This paper introduces a novel approach to the fine alignment of images in a burst captured by a handheld camera. In contrast to traditional techniques that estimate two-dimensional transformations between frame pairs or rely on discrete…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Bruno Lecouat , Yann Dubois de Mont-Marin , Théo Bodrito , Julien Mairal , Jean Ponce

We propose a new approach called LiDAR-Flow to robustly estimate a dense scene flow by fusing a sparse LiDAR with stereo images. We take the advantage of the high accuracy of LiDAR to resolve the lack of information in some regions of…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Ramy Battrawy , René Schuster , Oliver Wasenmüller , Qing Rao , Didier Stricker
‹ Prev 1 3 4 5 6 7 10 Next ›