Photometric Bundle Adjustment for Dense Multi-view 3D Modeling

112 citations recorded by the source corpus.

How researchers see this paper

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

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.”
Discrete optimization of ray potentials for semantic 3D reconstruction (2015, methodology): “The high quality refining of approximate mesh has also been formulated as a reprojection error minimization [26, 8].”
BA-Net: Dense Bundle Adjustment Network (2018, methodology): “In comparison, almost all conventional SfM algorithms [1, 51, 43, 17, 11] jointly optimize scene structures and camera motion via the Bundle-Adjustment (BA) algorithm [48, 3], which minimizes the geometric [1, 51, 43] or photometric [18, 17, 11] error through the Levenberg-Marquet(LM) algorithm.”
BARF: Bundle-Adjusting Neural Radiance Fields (2021, background): “BARF can be regarded as a type of photometric BA [8, 2, 26] using view synthesis as the proxy objec-tive.”
Colored Point Cloud Registration Revisited (2017, background): “Multi-view stereo pipelines reconstruct colored point clouds from image collections [8, 13, 39].”
BAD SLAM: Bundle Adjusted Direct RGB-D SLAM (2019, methodology): “Delaunoy & Pollefeys [8] propose an offline algorithm with a mesh-based object representation.”