Projects per year
We introduce a principled approach for synthesizing new views of a scene given a single source image. Previous methods for novel view synthesis can be divided into image-based rendering methods (e.g., flow prediction) or pixel generation methods. Flow predictions enable the target view to re-use pixels directly, but can easily lead to distorted results. Directly regressing pixels can produce structurally consistent results but generally suffer from the lack of low-level details. In this paper, we utilize an encoder-decoder architecture to regress pixels of a target view. In order to maintain details, we couple the decoder aligned feature maps with skip connections, where the alignment is guided by predicted depth map of the target view. Our experimental results show that our method does not suffer from distortions and successfully preserves texture details with aligned skip connections.
|Title of host publication||Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021|
|Number of pages||10|
|Publication status||Published - Jan 2021|
|MoE publication type||A4 Article in a conference publication|
|Event||IEEE Winter Conference on Applications of Computer Vision - Virtual, Online, United States|
Duration: 5 Jan 2021 → 9 Jan 2021
|Conference||IEEE Winter Conference on Applications of Computer Vision|
|Period||05/01/2021 → 09/01/2021|
FingerprintDive into the research topics of 'Novel view synthesis via depth-guided skip connections'. Together they form a unique fingerprint.
01/09/2017 → 31/08/2021
Project: Academy of Finland: Other research funding