Accurate, Dense, and Robust Multiview Stereopsis

By Yasutaka Furukawa, Jean Ponce. 2010

1,728 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis (2017, methodology): “a: reference model b: SurfaceNet c: camp [4] d: furu [8] e: tola [27] f: Gipuma [9]”
Learning a Multi-View Stereo Machine (2017, methodology): “use these classical constraints while also being able to reason about semantic shape cues from the data. Another approach to MVS involves representing the reconstruction as a collection of depth maps [6, 57, 41, 13, 40]. This allows recovery of ﬁne details for which a consistent global estimate may ”
OctNetFusion: Learning Depth Fusion from Data (2017, background): “While image based techniques [40, 15, 12, 49, 39] provide compelling results for sufficiently textured surfaces, the introduction of affordable depth sensors, in particular the Microsoft Kinect sensor, allows scanning a wide variety of objects and scenes.”
State of the art in high density image matching (2014, methodology): “Similar results were obtained with MicMac, while PMVS and Photoscan produced noisier and over-smoothed pro ﬁ les, respectively.”
Deep blending for free-viewpoint image-based rendering (2018, methodology): “Multi-view stereo algorithms (e.g., [Furukawa and Ponce 2010; Goe-sele et al. 2007; Jancosek and Pajdla 2011]) perform automatic 3D geometry reconstruction from unstructured photo datasets with diverse viewpoints.”
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction (2021, methodology): “Point- and surface-based reconstruction methods estimate the depth map of each pixel by exploiting inter-image photometric consistency [8] and then fuse the depth maps into a global dense point cloud [25, 48].”
A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos (2017, methodology): “PMVS and Gipuma produce very incomplete and noisy results while CMPMVS fails completely.”
A Survey on Structure from Motion (2017, methodology): “…relative pairwise pose estimation, camera modeling, global A snapshot of the dense 3D reconstruction obtained by using the PMVS package of [21, 22] with the motion estimate of [53] . camera orientation and location estimation, initial structure estimation, incremental SfM, motion and…”
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance (2020, methodology): “We compare to the following baselines: DVR [33] (for ﬁxed cameras), Colmap [40] (for ﬁxed and trained cameras) and Furu [9] (for ﬁxed cameras).”
Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video (2013, background): “Rigid structure from motion (SfM) algorithms have made significant progress towards this goal, with dense approaches to multi-view stereo (MVS) [14, 28] able to acquire highly accurate models from a collection of fully calibrated images.”
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo (2021, methodology): “Multi-view stereo (MVS) is a classical computer vision problem, aiming to achieve dense geometry reconstruction using images captured from multiple viewpoints, and has been extensively explored by various traditional methods [12, 24, 23, 14, 39, 16, 38].”
Street-view change detection with deconvolutional networks (2016, methodology): “Our method obtains a much higher density and number of 3D points than PMVS, which struggles on textureless regions.”
ARCH: Animatable Reconstruction of Clothed Humans (2020, background): “There are multiple attempts to solve this task with video inputs [2, 3, 37, 1, 52], RGB-D data [53, 56] and in multi-view settings [5, 13, 14, 45, 46, 47, 48, 6].”
PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction (2024, neutral): “Traditional methods adhere to the universal multi-view stereo pipeline, whichcanberoughlycategorizedbasedontheinterme-diate representation they rely on, such as point cloud [31], [32], volume [33], depth map [34], [35], [36], etc.”