AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis

Chonghyuk Song, Gengshan Yang, Kangle Deng, Jun-Yan Zhu, Deva Ramanan

ICCV 2023 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 16 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 depth supervision loss (ablation)Total-Recon · Ablation, 6 sequencesAcc@0.1m: .154 -> .898Improved
add depth supervision loss (ablation)Total-Recon · Ablation, 6 sequencesLPIPS: .372 -> .268Improved
add deformation field on top of root-body motion (ablation)Total-Recon · Ablation, 6 sequencesLPIPS: .296 -> .268Improved
add PoseNet initialization of root-body poses (ablation)Total-Recon · Ablation, 6 sequencesLPIPS: .293 -> .268Improved
add explicit root-body pose modelingTotal-Recon · Ablation, 6 sequencesconvergenceImproved
add depth supervision to HyperNeRF baselineHyperNeRF · Stereo-view synthesis meanAcc@0.1m: .198 -> .439Improved
add depth supervision to D2NeRF baselineD2NeRF · Stereo-view synthesis meanLPIPS: .611 -> .599No clear effect
hierarchical object-centric motion decomposition versus depth-supervised monocular deformable NeRFsTotal-Recon · Stereo-view synthesis meanLPIPS: .428 -> .278Improved

Later papers that compared with this method

2 later accepted papers report Total-Recon as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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