View morphing

By S. M. Seitz, Charles R. Dyer. 1996

Subfields: 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 Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

Unsupervised Learning of Depth and Ego-Motion from Video (2017, background): “A classic paradigm for view synthesis is to ﬁrst either estimate the underlying 3D geometry explicitly or establish pixel correspondence among input views, and then synthesize the novel views by compositing image patches from the input views (e.g., [4, 55, 43, 6, 9]).”
Deep Stereo: Learning to Predict New Views from the World's Imagery (2015, methodology): “These methods are largely hand-built and do not leverage training data.”
Gibson Env: Real-World Perception for Embodied Agents (2018, background): “View Synthesis and Image-Based Rendering: Rendering novel views of objects and scenes is one of the classic problems in vision and graphics [80, 84, 91, 23, 60].”
Video textures (2000, background): “Video textures can be combined with traditional image-based rendering algorithms such as view interpolation [5, 18, 24] to obtain three-dimensional video textures.”
Photorealistic Scene Reconstruction by Voxel Coloring (1997, methodology): “This scene can either be reprojected to synthesize new views as in [41], or used to compute correspondence maps for image-warping methods such as [8, 28, 30, 40, 38].”
Regenerative morphing (2010, methodology): “Regenerative Morphing can be applied to various scenarios, ranging from interpolation of views of rigid objects (also called view interpolation [6, 15, 9, 8]), to interpolating views of non-rigidly moving objects [14], to morphing between totally different images with no clear correspondences.”
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (2019, background): “Both classical warping algorithms [5, 28] and warping fields synthesized using machine learning (including deep learning) [11, 29, 40] can be used for such purposes.”
Nonlinear disparity mapping for stereoscopic 3D (2010, methodology): “For small scale interpolation, image-based view morphing is an alternative [Seitz and Dyer 1996; Mahajan et al. 2009].”
Modeling the World from Internet Photo Collections (2008, methodology): “More recent work in IBR has focused on techniques for new view synthesis, e.g., (Chen and Williams 1993; McMillan and Bishop 1995; Gortler et al. 1996; Levoy and Hanrahan 1996; Seitz and Dyer 1996; Aliaga et al. 2003; Zitnick et al. 2004; Buehler et al. 2001).”
Plenoptic sampling (2000, background): “com interpolation [7], view morphing [21] and layered-depth images (LDI) [22], LDI tree [6], etc.”
Review of image-based rendering techniques (2000, background): “Ontheotherhand,view morphing[37] generatesin-betweencameramatrices alongtheline of two original cameracenters,basedon point correspondences.”
Im2Pano3D: Extrapolating 360° Structure and Semantics Beyond the Field of View (2017, background): “Traditional view synthesis works [30, 29] represent observations and new views using a set of disjoint images with their camera parameters.”
Survey of image-based representations and compression techniques (2003, methodology): “On the other hand, view morphing [75] results in in-between camera matrices along the line of two original camera centers based on point correspondences.”
3D generic object categorization, localization and pose estimation (2007, result): “It is interesting to compare these constraints with those introduced in [22].”
Free View Synthesis (2020, background): “Early light-ﬁeld meth-ods [14,24,36] do not require any information about the scene geometry, but either require a fairly dense and regularly-spaced camera grid, or restrict the target view to be a linear combination of the source views.”
Exploring photobios (2011, methodology): “, [Chen and Williams 1993; Seitz and Dyer 1996; Levoy and Hanrahan 1996] to handle changes in expression, age, and other transformations.”