A 3D-degradation-aware feature extractor, combining depth-based warping and a restoration head, improves GNeRF reconstruction from degraded source images, and the Objaverse Blur Dataset provides a large-scale benchmark for this task.
Simple baselines for image restoration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Degradation-Robust Reconstruction in Generalizable NeRF
A 3D-degradation-aware feature extractor, combining depth-based warping and a restoration head, improves GNeRF reconstruction from degraded source images, and the Objaverse Blur Dataset provides a large-scale benchmark for this task.