Thread by @ilkedemir

For the night session attendees of #CVPR2020, here is my completely non-scientifically chosen top five papers @cvpr first day. Visit them in the next 8 hours! (1/6)

1. Perspective Plane Program Induction From a Single Image
Authors: Yikai Li, Jiayuan Mao, Xiuming Zhang, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu @MIT_CSAIL

Domain agnostic image-based proceduralization with single terminal and grid-based rules.

#CVPR2020 Day 1

2. Learning Formation of Physically-Based Face Attributes

Authors: Ruilong Li, Karl Bladin, Yajie Zhao, Chinmay Chinara, Owen Ingraham, Pengda Xiang, Xinglei Ren, et al. @HaoLi81

Photorealistic humans are here! Fitting code for any 3D mesh is coming soon too.

#CVPR2020 Day 1

3. Meshlet Priors for 3D Mesh Reconstruction
Authors: Abhishek Badki, @0razio, @jankautz, Pradeep Sen

Between our near-convex decomposition and the atlasnet, there is meshlets, another representation to learn the geometry.

#CVPR2020 Day 1

4. SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
Authors: Yue Jiang, Dantong Ji, Zhizhong Han, Matthias Zwicker

Use differentiable rendering and local SDF grids, minimize (image+geometry+SDF) loss, and voila, la reconstruction!

#CVPR2020

5. CvxNet: Learnable Convex Decomposition

Authors: Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, @taiyasaki

SIF, meshlet, atlases, and now... convexes for learnable shape covers!

#CVPR2020 Day 1

Bonus: Shameless plug, convex decomposition is also good for your 3D printers :) No support material and 35-65% faster printing!

Paper: sciencedirect.com/science/articl…

Non-CVPR :)