most citedStructure from Motion for Panorama-Style Videos

5 citations · 9 across the 2 of their papers we have counts for

collaborators

9 papers

cs.CV20202 cited

Reconstructing NBA Players

Luyang Zhu, Konstantinos Rematas, Brian Curless +2

Great progress has been made in 3D body pose and shape estimation from a single photo. Yet, state-of-the-art results still suffer from errors due to challenging body poses, modelin…

cs.CV2020

People as Scene Probes

Yifan Wang, Brian Curless, Steve Seitz

By analyzing the motion of people and other objects in a scene, we demonstrate how to infer depth, occlusion, lighting, and shadow information from video taken from a single camera…

cs.CV2020

Background Matting: The World is Your Green Screen

Soumyadip Sengupta, Vivek Jayaram, Brian Curless +2

We propose a method for creating a matte -- the per-pixel foreground color and alpha -- of a person by taking photos or videos in an everyday setting with a handheld camera. Most e…

cs.CV2020

Seeing the World in a Bag of Chips

Jeong Joon Park, Aleksander Holynski, Steve Seitz

We address the dual problems of novel view synthesis and environment reconstruction from hand-held RGBD sensors. Our contributions include 1) modeling highly specular objects, 2) m…

cs.CV2019

KeystoneDepth: Visualizing History in 3D

Xuan Luo, Yanmeng Kong, Jason Lawrence +2

This paper introduces the largest and most diverse collection of rectified stereo image pairs to the research community, KeystoneDepth, consisting of tens of thousands of stereogra…

cs.CV20195 cited

Structure from Motion for Panorama-Style Videos

Chris Sweeney, Aleksander Holynski, Brian Curless +1

We present a novel Structure from Motion pipeline that is capable of reconstructing accurate camera poses for panorama-style video capture without prior camera intrinsic calibratio…