AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video

Edgar Tretschk, Ayush Tewari, Vladislav Golyanik, Michael Zollhöfer, Christoph Lassner, Christian Theobalt

ICCV 2021 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 477 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 the divergence loss (ablation)NR-NeRF · Dynamic scenes, novel viewsforeground stability (qualitative)Improved
add the rigidity network and offsets losses together (ablation)NR-NeRF · Dynamic scenes, novel viewsbackground stability (std of pixel colour over time)Improved
apply offsets loss to raw offsets and rigidity separately rather than to masked offsets (ablation)NR-NeRF · Dynamic scenes, novel viewsbackground stabilityImproved
add the rigidity network (ablation)NR-NeRF · Dynamic scenes, novel viewsbackground stabilityImproved
deform with ray bending instead of conditioning the volume on latent codeNR-NeRF vs naive NR-NeRF · Dynamic scenes (18 scenes, test frames)SSIM: 0.738 -> 0.758Improved
ray bending instead of naive latent conditioningNR-NeRF vs naive NR-NeRF · Dynamic scenes (18 scenes, test frames)PSNR: 25.83 -> 24.70Hurt
ray bending instead of naive latent conditioningNR-NeRF vs naive NR-NeRF · Dynamic scenes (18 scenes, test frames)LPIPS: 0.226 -> 0.197Improved
deform with ray bending vs rigid NeRF (view cond.)NR-NeRF · Dynamic scenes (18 scenes, test frames)PSNR: 22.24 -> 24.70Improved
add approximate view conditioningNR-NeRF · Dynamic scenes (18 scenes, test frames)PSNR: 24.70 -> 25.15Improved
add exact view conditioningNR-NeRF · Dynamic scenes (18 scenes, test frames)LPIPS: 0.197 -> 0.190Improved
condition on viewing direction in multi-view dataNR-NeRF · Multi-view capturesmoke-like artifacts (qualitative)Improved
use ray bending vs Neural Volumes on monocular inputNR-NeRF · Dynamic scenes (18 scenes, test frames)PSNR: 14.13 -> 24.70Improved

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