Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324108786> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4324108786 abstract "Recently, Neural Radiance Fields (NeRF) have emerged as a potent method for synthesizing novel views from a dense set of images. Despite its impressive performance, NeRF is plagued by its necessity for numerous calibrated views and its accuracy diminishes significantly in a few-shot setting. To address this challenge, we propose Self-NeRF, a self-evolved NeRF that iteratively refines the radiance fields with very few number of input views, without incorporating additional priors. Basically, we train our model under the supervision of reference and unseen views simultaneously in an iterative procedure. In each iteration, we label unseen views with the predicted colors or warped pixels generated by the model from the preceding iteration. However, these expanded pseudo-views are afflicted by imprecision in color and warping artifacts, which degrades the performance of NeRF. To alleviate this issue, we construct an uncertainty-aware NeRF with specialized embeddings. Some techniques such as cone entropy regularization are further utilized to leverage the pseudo-views in the most efficient manner. Through experiments under various settings, we verified that our Self-NeRF is robust to input with uncertainty and surpasses existing methods when trained on limited training data." @default.
- W4324108786 created "2023-03-14" @default.
- W4324108786 creator A5009275869 @default.
- W4324108786 creator A5032474064 @default.
- W4324108786 creator A5059141031 @default.
- W4324108786 creator A5073696293 @default.
- W4324108786 creator A5076859280 @default.
- W4324108786 date "2023-03-10" @default.
- W4324108786 modified "2023-10-16" @default.
- W4324108786 title "Self-NeRF: A Self-Training Pipeline for Few-Shot Neural Radiance Fields" @default.
- W4324108786 doi "https://doi.org/10.48550/arxiv.2303.05775" @default.
- W4324108786 hasPublicationYear "2023" @default.
- W4324108786 type Work @default.
- W4324108786 citedByCount "0" @default.
- W4324108786 crossrefType "posted-content" @default.
- W4324108786 hasAuthorship W4324108786A5009275869 @default.
- W4324108786 hasAuthorship W4324108786A5032474064 @default.
- W4324108786 hasAuthorship W4324108786A5059141031 @default.
- W4324108786 hasAuthorship W4324108786A5073696293 @default.
- W4324108786 hasAuthorship W4324108786A5076859280 @default.
- W4324108786 hasBestOaLocation W43241087861 @default.
- W4324108786 hasConcept C107673813 @default.
- W4324108786 hasConcept C120665830 @default.
- W4324108786 hasConcept C121332964 @default.
- W4324108786 hasConcept C153083717 @default.
- W4324108786 hasConcept C154945302 @default.
- W4324108786 hasConcept C157202957 @default.
- W4324108786 hasConcept C160633673 @default.
- W4324108786 hasConcept C177264268 @default.
- W4324108786 hasConcept C177769412 @default.
- W4324108786 hasConcept C199360897 @default.
- W4324108786 hasConcept C23690007 @default.
- W4324108786 hasConcept C2984842247 @default.
- W4324108786 hasConcept C31972630 @default.
- W4324108786 hasConcept C41008148 @default.
- W4324108786 hasConcept C50644808 @default.
- W4324108786 hasConcept C9679016 @default.
- W4324108786 hasConceptScore W4324108786C107673813 @default.
- W4324108786 hasConceptScore W4324108786C120665830 @default.
- W4324108786 hasConceptScore W4324108786C121332964 @default.
- W4324108786 hasConceptScore W4324108786C153083717 @default.
- W4324108786 hasConceptScore W4324108786C154945302 @default.
- W4324108786 hasConceptScore W4324108786C157202957 @default.
- W4324108786 hasConceptScore W4324108786C160633673 @default.
- W4324108786 hasConceptScore W4324108786C177264268 @default.
- W4324108786 hasConceptScore W4324108786C177769412 @default.
- W4324108786 hasConceptScore W4324108786C199360897 @default.
- W4324108786 hasConceptScore W4324108786C23690007 @default.
- W4324108786 hasConceptScore W4324108786C2984842247 @default.
- W4324108786 hasConceptScore W4324108786C31972630 @default.
- W4324108786 hasConceptScore W4324108786C41008148 @default.
- W4324108786 hasConceptScore W4324108786C50644808 @default.
- W4324108786 hasConceptScore W4324108786C9679016 @default.
- W4324108786 hasLocation W43241087861 @default.
- W4324108786 hasOpenAccess W4324108786 @default.
- W4324108786 hasPrimaryLocation W43241087861 @default.
- W4324108786 hasRelatedWork W2116300362 @default.
- W4324108786 hasRelatedWork W2143630701 @default.
- W4324108786 hasRelatedWork W2172117717 @default.
- W4324108786 hasRelatedWork W2370766994 @default.
- W4324108786 hasRelatedWork W2538483272 @default.
- W4324108786 hasRelatedWork W2621079708 @default.
- W4324108786 hasRelatedWork W2779438614 @default.
- W4324108786 hasRelatedWork W3190512878 @default.
- W4324108786 hasRelatedWork W4225711786 @default.
- W4324108786 hasRelatedWork W4308948894 @default.
- W4324108786 isParatext "false" @default.
- W4324108786 isRetracted "false" @default.
- W4324108786 workType "article" @default.