AI Paper Atlas

Research map / 3D vision / 3D generation

Rotationally-Temporally Consistent Novel View Synthesis of Human Performance Video

Youngjoong Kwon, Stefano Petrangeli, Dahun Kim, Haoliang Wang, Eunbyung Park, Viswanathan Swaminathan, Henry Fuchs

ECCV 2020 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 15 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 rotational consistency supervision (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)L1: .0825 -> .0736Improved
add rotational consistency supervision (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)Rotational loss: .0433 -> .0390Improved
add rotational consistency supervision (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)Temporal loss: .0280 -> .0163Improved
add rotational consistency supervision (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)SSIM: .7364 -> .7541Improved
add temporal consistency supervision (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)Temporal loss: .0280 -> .0149Improved
add temporal consistency supervision (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)L1: .0825 -> .0743Improved
add temporal consistency supervision (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)Rotational loss: .0433 -> .0414Improved
add both rotational and temporal consistency (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)L1: .0825 -> .0722Improved
add both rotational and temporal consistency (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)Temporal loss: .0280 -> .0146Improved
add both rotational and temporal consistency (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)SSIM: .7364 -> .7596Improved
add rotational and temporal consistency on top of TC alone (ablation)Base siamese network · MVHA ablation (seen model, unseen pose)L1: .0743 -> .0722Improved
use proposed siamese network with gating instead of TBNOurs · MVHA (unseen model, unseen pose)L1: .1130 -> .0863Improved

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