In this paper, we tackle the problem of generating a novel image from an arbitrary viewpoint given a single frame as input. While existing methods operating in this setup aim at predicting the target view depth map to guide the synthesis, without explicit supervision over such a task, we jointly optimize our framework for both novel view synthesis and depth estimation to unleash the synergy between the two at its best. Specifically, a shared depth decoder is trained in a self-supervised manner to predict depth maps that are consistent across the source and target views. Our results demonstrate the effectiveness of our approach in addressing the challenges of both tasks allowing for higher-quality generated images, as well as more accurate depth for the target viewpoint.

Depth Self-Supervision for Single Image Novel View Synthesis / Minelli G.; Poggi M.; Salti S.. - ELETTRONICO. - (2023), pp. 5836-5843. (Intervento presentato al convegno International Conference on Intelligent Robots and Systems tenutosi a Detroit, Michigan, USA nel October 1 – 5, 2023) [10.1109/IROS55552.2023.10342058].

Depth Self-Supervision for Single Image Novel View Synthesis

Minelli G.;Poggi M.;Salti S.
2023

Abstract

In this paper, we tackle the problem of generating a novel image from an arbitrary viewpoint given a single frame as input. While existing methods operating in this setup aim at predicting the target view depth map to guide the synthesis, without explicit supervision over such a task, we jointly optimize our framework for both novel view synthesis and depth estimation to unleash the synergy between the two at its best. Specifically, a shared depth decoder is trained in a self-supervised manner to predict depth maps that are consistent across the source and target views. Our results demonstrate the effectiveness of our approach in addressing the challenges of both tasks allowing for higher-quality generated images, as well as more accurate depth for the target viewpoint.
2023
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
5836
5843
Depth Self-Supervision for Single Image Novel View Synthesis / Minelli G.; Poggi M.; Salti S.. - ELETTRONICO. - (2023), pp. 5836-5843. (Intervento presentato al convegno International Conference on Intelligent Robots and Systems tenutosi a Detroit, Michigan, USA nel October 1 – 5, 2023) [10.1109/IROS55552.2023.10342058].
Minelli G.; Poggi M.; Salti S.
File in questo prodotto:
File Dimensione Formato  
23_IROS_Depth self-supervision for single image novel view synthesis.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 4.9 MB
Formato Adobe PDF
4.9 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/959831
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact