SVS: Adversarial refinement for sparse novel view synthesis

November 14, 2022 Β· Declared Dead Β· πŸ› British Machine Vision Conference

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Violeta MenΓ©ndez GonzΓ‘lez, Andrew Gilbert, Graeme Phillipson, Stephen Jolly, Simon Hadfield arXiv ID 2211.07301 Category cs.CV: Computer Vision Cross-listed cs.GR, cs.LG Citations 3 Venue British Machine Vision Conference Last Checked 3 months ago
Abstract
This paper proposes Sparse View Synthesis. This is a view synthesis problem where the number of reference views is limited, and the baseline between target and reference view is significant. Under these conditions, current radiance field methods fail catastrophically due to inescapable artifacts such 3D floating blobs, blurring and structural duplication, whenever the number of reference views is limited, or the target view diverges significantly from the reference views. Advances in network architecture and loss regularisation are unable to satisfactorily remove these artifacts. The occlusions within the scene ensure that the true contents of these regions is simply not available to the model. In this work, we instead focus on hallucinating plausible scene contents within such regions. To this end we unify radiance field models with adversarial learning and perceptual losses. The resulting system provides up to 60% improvement in perceptual accuracy compared to current state-of-the-art radiance field models on this problem.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computer Vision

Died the same way β€” πŸ‘» Ghosted