03-epipolar-geometry.pdf

N/A

CS231A Course Notes 3: Epipolar Geometry Kenji Hata and Silvio Savarese 1 Introduction Previously, we have seen how to compute the intrinsic and extrinsic param- eters of a camera using one or more views using a typical camera calibration procedure or single view metrology. This process culminated in deriving properties about the 3D world from one image. However, in general, it is not possible to recover the entire structure of the 3D world from just one image. This is due to the intrinsic ambiguity of the 3D to the 2D mapping: some information is simply lost.…

related reading

• Perspective-n-Point - Wikipediaen.wikipedia.org
• 01-camera-models.pdfweb.stanford.edu
• DUSt3R: Geometric 3D Vision Made Easyarxiv.org
• 3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimationarxiv.org
• Homography - Wikipediaen.wikipedia.org
• Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dresearch.nvidia.com
• https://www.deeplearningbook.org/contents/linear_algebra.htmldeeplearningbook.org
• Point-set registrationen.wikipedia.org
• [2008.05711] Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Darxiv.org
• Perspective Distortions: Why Normal Cameras Make Faces Look Weird | Aaron Hertzmann’s blogaaronhertzmann.com
• [2510.15271] CuSfM: CUDA-Accelerated Structure-from-Motionarxiv.org
• Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencetelling-left-from-right.github.io