AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

SPARF: Neural Radiance Fields From Sparse and Noisy Poses

Prune Truong, Marie-Julie Rakotosaona, Fabian Manhardt, Federico Tombari

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 135 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add multi-view correspondence supervision to sparse-view NeRF (ablation)SPARF on DTU with fixed ground-truth poses · DTU, 3 viewsPSNR: 16.27 -> 18.13Improved
Add depth consistency loss to multi-view correspondence loss (ablation)SPARF on DTU with fixed ground-truth poses · DTU, 3 viewsPSNR: 18.13 -> 18.30Improved
Use depth consistency loss alone, without multi-view correspondence loss (ablation)SPARF on DTU with fixed ground-truth poses · DTU, 3 viewsPSNR: 16.27 -> 15.86Hurt
Use coarse-to-fine positional encoding instead of full high-frequency encoding (ablation)NeRF on DTU with fixed ground-truth poses · DTU, 3 viewsPSNR: 8.41 -> 16.27Improved
Remove positional encoding (ablation)NeRF on DTU with fixed ground-truth poses · DTU, 3 viewsPSNR: 8.41 -> 16.11Improved
Use a smaller MLP (ablation)NeRF on DTU with fixed ground-truth poses · DTU, 3 viewsPSNR: 8.41 -> 9.03No clear effect
Replace per-image ground-truth depth supervision with ground-truth 3D-point supervision (ablation)Joint pose-NeRF training on DTU with noisy poses · DTU, 3 viewsrotation error: 7.3 -> 0.4Improved
Add multi-view correspondence loss to photometric training (ablation)Joint pose-NeRF training on DTU with noisy poses · DTU, 3 viewsrotation error: 10.3 -> 1.85Improved
Add a mask loss to photometric training (ablation)Joint pose-NeRF training on DTU with noisy poses · DTU, 3 viewsrotation error: 10.3 -> 13.2Hurt
Add multi-view correspondence and jointly refine poses and NeRFSPARF · DTU, 3 views, noisy posesPSNR: 12.04 -> 17.74Improved
Use SPARF rather than RegBARF for sparse pose refinementNeRF pose refinement · LLFF, 3 views, identity posesPSNR: 18.57 -> 19.58Improved
Use SPARF rather than DS-NeRF for sparse pose refinementNeRF pose refinement · Replica, 3 views, COLMAP posesPSNR: 24.75 -> 26.98Improved

Later papers that compared with this method

9 later accepted papers report SPARF as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

1 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy