activity
20162022
most citedFront2Back: Single View 3D Shape Reconstruction via Front to Back Prediction

3 citations · 11 across the 10 of their papers we have counts for

collaborators

24 papers

cs.CV2022

Scaling Neural Face Synthesis to High FPS and Low Latency by Neural Caching

Frank Yu, Sid Fels, Helge Rhodin

Recent neural rendering approaches greatly improve image quality, reaching near photorealism. However, the underlying neural networks have high runtime, precluding telepresence and…

cs.CV2022

A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset

Eric Hedlin, Helge Rhodin, Kwang Moo Yi

Many human pose estimation methods estimate Skinned Multi-Person Linear (SMPL) models and regress the human joints from these SMPL estimates. In this work, we show that the most wi…

cs.CV2021

NRST: Non-rigid Surface Tracking from Monocular Video

Marc Habermann, Weipeng Xu, Helge Rhodin +3

We propose an efficient method for non-rigid surface tracking from monocular RGB videos. Given a video and a template mesh, our algorithm sequentially registers the template non-ri…

cs.CV2021

TriPose: A Weakly-Supervised 3D Human Pose Estimation via Triangulation from Video

Mohsen Gholami, Ahmad Rezaei, Helge Rhodin +2

Estimating 3D human poses from video is a challenging problem. The lack of 3D human pose annotations is a major obstacle for supervised training and for generalization to unseen da…

cs.CV2021

A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose

Shih-Yang Su, Frank Yu, Michael Zollhoefer +1

While deep learning reshaped the classical motion capture pipeline with feed-forward networks, generative models are required to recover fine alignment via iterative refinement. Un…

cs.CV2020

Human Detection and Segmentation via Multi-view Consensus

Isinsu Katircioglu, Helge Rhodin, Jörg Spörri +2

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive a…