Lune

CVPR2021Top-tier venue

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

Tomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Kanazawa

2021Year
34Top-tier citations

Abstract

Figure 1 : Controlling shape deformation with unsupervised 3D keypoints. We discover unsupervised 3D keypoints that allow for intuitive control of an object's shape. This figure shows individual steps of interactive control. The red arrows illustrate the direction in which the keypoints are manipulated. Note that the resulting deformations are localized and object parts are deformed in an intuitive manner-e.g., moving keypoints at the tip of the wings backward moves the wings backwards-all while preserving the details of the original shape.

Ask about this paper

Your agent reads all of it.

Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.

Questions to start from

Your agent calls

Luneget_paper_fulltext

Ask in Lune

Free to start. No credit card required.

lune papers fulltext 67971dce-73f7-4f43-9374-a4b0012f072d

Cited by top-tier papers34

Ask how each one uses it

Builds on8

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines