activity
20162022
most citedShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis

79 citations · 226 across the 27 of their papers we have counts for

collaborators
Showing 2017Show all

6 papers · 1 filter

cs.GR2017

Joint Material and Illumination Estimation from Photo Sets in the Wild

Tuanfeng Y. Wang, Tobias Ritschel, Niloy J. Mitra

Faithful manipulation of shape, material, and illumination in 2D Internet images would greatly benefit from a reliable factorization of appearance into material (i.e., diffuse and…

cs.CV201710 cited

SeeThrough: Finding Chairs in Heavily Occluded Indoor Scene Images

Moos Hueting, Pradyumna Reddy, Vladimir Kim +3

Discovering 3D arrangements of objects from single indoor images is important given its many applications including interior design, content creation, etc. Although heavily researc…

cs.CV20178 cited

Learning to Represent Mechanics via Long-term Extrapolation and Interpolation

Sébastien Ehrhardt, Aron Monszpart, Andrea Vedaldi +1

While the basic laws of Newtonian mechanics are well understood, explaining a physical scenario still requires manually modeling the problem with suitable equations and associated…

cs.CV2017

DepthCut: Improved Depth Edge Estimation Using Multiple Unreliable Channels

Paul Guerrero, Holger Winnemöller, Wilmot Li +1

In the context of scene understanding, a variety of methods exists to estimate different information channels from mono or stereo images, including disparity, depth, and normals. A…

cs.AI201738 cited

Learning A Physical Long-term Predictor

Sebastien Ehrhardt, Aron Monszpart, Niloy J. Mitra +1

Evolution has resulted in highly developed abilities in many natural intelligences to quickly and accurately predict mechanical phenomena. Humans have successfully developed laws o…

cs.GR2017

Plausible Shading Decomposition For Layered Photo Retouching

Carlo Innamorati, Tobias Ritschel, Tim Weyrich +1

Photographers routinely compose multiple manipulated photos of the same scene (layers) into a single image, which is better than any individual photo could be alone. Similarly, 3D…