Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386065515> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4386065515 abstract "Novel view synthesis with sparse inputs is a challenging problem for neural radiance fields (NeRF). Recent efforts alleviate this challenge by introducing external supervision, such as pre-trained models and extra depth signals, or by using non-trivial patch-based rendering. In this paper, we present Frequency regularized NeRF (FreeNeRF), a surprisingly simple baseline that outperforms previous methods with minimal modifications to plain NeRF. We analyze the key challenges in few-shot neural rendering and find that frequency plays an important role in NeRF's training. Based on this analysis, we propose two regularization terms: one to regularize the frequency range of NeRF's inputs, and the other to penalize the near-camera density fields. Both techniques are “free lunches” that come at no additional computational cost. We demonstrate that even with just one line of code change, the original NeRF can achieve similar performance to other complicated methods in the few-shot setting. FreeNeRF achieves state-of-the-art performance across diverse datasets, including Blender, DTU, and LLFF. We hope that this simple baseline will motivate a rethinking of the fundamental role of frequency in NeRF's training, under both the low-data regime and beyond. This project is released at FreeNeRF." @default.
- W4386065515 created "2023-08-23" @default.
- W4386065515 creator A5033632697 @default.
- W4386065515 creator A5039055847 @default.
- W4386065515 creator A5050003000 @default.
- W4386065515 date "2023-06-01" @default.
- W4386065515 modified "2023-09-26" @default.
- W4386065515 title "FreeNeRF: Improving Few-Shot Neural Rendering with Free Frequency Regularization" @default.
- W4386065515 cites W2085905957 @default.
- W4386065515 cites W2964288609 @default.
- W4386065515 cites W3172568571 @default.
- W4386065515 cites W3176327543 @default.
- W4386065515 cites W3176368002 @default.
- W4386065515 cites W3202995573 @default.
- W4386065515 cites W3203257492 @default.
- W4386065515 cites W3204859697 @default.
- W4386065515 cites W3215769467 @default.
- W4386065515 cites W3216476011 @default.
- W4386065515 cites W4214564845 @default.
- W4386065515 cites W4214731463 @default.
- W4386065515 cites W4288242633 @default.
- W4386065515 cites W4297846303 @default.
- W4386065515 cites W4312480149 @default.
- W4386065515 cites W4312679369 @default.
- W4386065515 cites W4312708649 @default.
- W4386065515 cites W4312969460 @default.
- W4386065515 cites W4313154783 @default.
- W4386065515 doi "https://doi.org/10.1109/cvpr52729.2023.00798" @default.
- W4386065515 hasPublicationYear "2023" @default.
- W4386065515 type Work @default.
- W4386065515 citedByCount "0" @default.
- W4386065515 crossrefType "proceedings-article" @default.
- W4386065515 hasAuthorship W4386065515A5033632697 @default.
- W4386065515 hasAuthorship W4386065515A5039055847 @default.
- W4386065515 hasAuthorship W4386065515A5050003000 @default.
- W4386065515 hasConcept C120665830 @default.
- W4386065515 hasConcept C121332964 @default.
- W4386065515 hasConcept C127413603 @default.
- W4386065515 hasConcept C154945302 @default.
- W4386065515 hasConcept C205711294 @default.
- W4386065515 hasConcept C23690007 @default.
- W4386065515 hasConcept C2776135515 @default.
- W4386065515 hasConcept C2984842247 @default.
- W4386065515 hasConcept C2992734406 @default.
- W4386065515 hasConcept C41008148 @default.
- W4386065515 hasConcept C50644808 @default.
- W4386065515 hasConcept C78519656 @default.
- W4386065515 hasConceptScore W4386065515C120665830 @default.
- W4386065515 hasConceptScore W4386065515C121332964 @default.
- W4386065515 hasConceptScore W4386065515C127413603 @default.
- W4386065515 hasConceptScore W4386065515C154945302 @default.
- W4386065515 hasConceptScore W4386065515C205711294 @default.
- W4386065515 hasConceptScore W4386065515C23690007 @default.
- W4386065515 hasConceptScore W4386065515C2776135515 @default.
- W4386065515 hasConceptScore W4386065515C2984842247 @default.
- W4386065515 hasConceptScore W4386065515C2992734406 @default.
- W4386065515 hasConceptScore W4386065515C41008148 @default.
- W4386065515 hasConceptScore W4386065515C50644808 @default.
- W4386065515 hasConceptScore W4386065515C78519656 @default.
- W4386065515 hasLocation W43860655151 @default.
- W4386065515 hasOpenAccess W4386065515 @default.
- W4386065515 hasPrimaryLocation W43860655151 @default.
- W4386065515 hasRelatedWork W2978679497 @default.
- W4386065515 hasRelatedWork W3046201580 @default.
- W4386065515 hasRelatedWork W3092108389 @default.
- W4386065515 hasRelatedWork W3107529234 @default.
- W4386065515 hasRelatedWork W3141231837 @default.
- W4386065515 hasRelatedWork W3179022832 @default.
- W4386065515 hasRelatedWork W4287589431 @default.
- W4386065515 hasRelatedWork W4290803075 @default.
- W4386065515 hasRelatedWork W4312819713 @default.
- W4386065515 hasRelatedWork W4353112993 @default.
- W4386065515 isParatext "false" @default.
- W4386065515 isRetracted "false" @default.
- W4386065515 workType "article" @default.