Geometric modeling for computer vision.

By Bruce G. Baumgart. 1974

How researchers see this paper

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

Citations in the corpus

Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction (2019, background): “The standpoint of viewing vision problems as inverse graphics has been investigated since the very beginning of the field [3, 55, 32].”
Learning to Navigate the Energy Landscape (2016, background): “It has been explored by researchers many times [16, 4, 45, 49] but repeatedly fell out of favor due to the perception of being computationally expensive and brittle due to reconstruc-”
Range sensor and silhouette fusion for high-quality 3D Scanning (2015, background): “In particular, the visual hull attempts to reconstruct an object purely from silhouettes captured from multiple views [4].”
Multi-View Stereo: A Tutorial (2015, background): “Similarly, in early days, many algorithms initialized meshes based on the visual hull [35].”
3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare (2018, background): “The idea of analysis-by-synthesis can be traced back to Helmhotz’s 1867 work on unconscious inference [21], and it has a long history [3, 26, 61, 23, 9].”
DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing (2019, methodology): “In the realm of 3D geometry understanding, this approach has been used since the very early age [1, 35, 54].”
Differentiable Monte Carlo ray tracing through edge sampling (2018, unknown): “Vision as inverse graphics has a long history in both computer graphics and vision (e.g. [Baumgart 1974; Patow and Pueyo 2003; Yu et al. 1999]).”
The informed sampler: A discriminative approach to Bayesian inference in generative computer vision models (2014, background): “We concentrate on the problem of inverting an existing graphics rendering engine, an approach that can be understood as “Inverse Graphics”.”
OpenDR: An Approximate Differentiable Renderer (2014, background): “The model can take many forms of varying realism but, when the model and rendering process are designed to produce realistic images, this process is often called inverse graphics [3,33].”
Inverse Graphics with Probabilistic CAD Models (2014, background): “erformance improvements over state-of-the-art baselines. 1 Introduction Formulations of vision problems as probabilistic inversions of generative models based on computer graphics have a long history [2, 20] and have recently attracted renewed attention [9, 7, 6]. However, applications to 3D object ”
Indirect deep structured learning for 3D human body shape and pose prediction (2017, background): “Inverse graphics [1, 19] is the problem of recovering the underlying scene components by learning to render a target scene.”
Accurate, Dense, and Robust Multi-View Stereopsis (2007, background): “Algorithms based on deformable polygonal meshes [10], [11], [12] demand a good starting point—for example, a visual hull model [13]—to initialize the corresponding optimization process, which limits their applicability.”
Accurate, Dense, and Robust Multiview Stereopsis (2010, background): “Algorithms based on deformable polygonal meshes [10], [11], [12] demand a good starting point —for example, a visual hull model [13]—to initialize the corresponding optimization process, which limits their applicability.”