activity
20192026
most citedReal-time Deep Dynamic Characters

118 citations · 275 across the 10 of their papers we have counts for

collaborators
Showing 2022Show all

5 papers · 1 filter

cs.CV2022

Neural Pixel Composition: 3D-4D View Synthesis from Multi-Views

Aayush Bansal, Michael Zollhoefer

We present Neural Pixel Composition (NPC), a novel approach for continuous 3D-4D view synthesis given only a discrete set of multi-view observations as input. Existing state-of-the…

cs.RO2022

iSDF: Real-Time Neural Signed Distance Fields for Robot Perception

Joseph Ortiz, Alexander Clegg, Jing Dong +4

We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction. Given a stream of posed depth images from a moving camera, it trains a random…

cs.CV2022

KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints

Marko Mihajlovic, Aayush Bansal, Michael Zollhoefer +2

Image-based volumetric humans using pixel-aligned features promise generalization to unseen poses and identities. Prior work leverages global spatial encodings and multi-view geome…

cs.CV2022

COAP: Compositional Articulated Occupancy of People

Marko Mihajlovic, Shunsuke Saito, Aayush Bansal +2

We present a novel neural implicit representation for articulated human bodies. Compared to explicit template meshes, neural implicit body representations provide an efficient mech…

cs.HC2022★ 5 cited

Mutual Scene Synthesis for Mixed Reality Telepresence

Mohammad Keshavarzi, Michael Zollhoefer, Allen Y. Yang +2

Remote telepresence via next-generation mixed reality platforms can provide higher levels of immersion for computer-mediated communications, allowing participants to engage in a wi…