Published on:
7 December 2023
Primary Category:
Computer Vision and Pattern Recognition
Paper Authors:
Chuanxia Zheng,
Andrea Vedaldi
Encodes target views via distributed per-pixel ray conditioning
Improves multi-view consistency with attention & noise sharing
Avoids expensive 3D representations used in other works
Demonstrates excellent generalization to unseen categories
Outperforms recent state-of-the-art models on pose accuracy
Consistent view synthesis without 3D
This paper introduces Free3D, a novel approach for generating consistent 360-degree novel views from a single input image, without needing slow and memory-intensive explicit 3D representations. It achieves this through a new per-pixel ray conditioning technique to precisely encode target camera poses, alongside multi-view attention and noise sharing for improved consistency.
No comments yet, be the first to start the conversation...
Sign up to comment on this paper