AI Paper Atlas

Research map / 3D vision / 3D generation

View Synthesis of Dynamic Scenes Based on Deep 3D Mask Volume

Kai‐En Lin, Guowei Yang, Lei Xiao, Feng Liu, Ravi Ramamoorthi

TPAMI 2023 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 26 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
replace 2D mask with 3D mask volume (ablation)MPI blending pipeline · Real multi-view video dataset (cameras 4,5 input)STRRED: 0.2892 -> 0.1683Improved
replace 2D mask with 3D mask volume (ablation)MPI blending pipeline · Real multi-view video dataset (cameras 4,5 input)PSNR: 25.50 -> 26.22Improved
add 3D mask volume with background MPI to per-frame MPI/LLFFMPI/LLFF · Real multi-view video dataset (cameras 4,5 input)STRRED: 0.2917 -> 0.1683Improved
replace 2D mask with 3D mask volume (ablation)MPI blending pipeline · Synthetic dataset (cameras 4,5 input)STRRED: 0.5428 -> 0.2812Improved
add 3D mask volume to MPI/LLFFMPI/LLFF · Synthetic dataset (cameras 4,5 input)STRRED: 0.2889 -> 0.2812No clear effect
add 3D mask volume to MPI/LLFFMPI/LLFF · Synthetic dataset (cameras 4,5 input)PSNR: 26.1167 -> 26.1348No clear effect
use 2D mask instead of no mask (ablation)MPI/LLFF · Real multi-view video dataset (cameras 4,5 input)STRRED: 0.2917 -> 0.2892No clear effect
add mask sparsity loss Ls (ablation)Ours · Real multi-view video dataset (cameras 4,5 input)STRRED: 0.1683 -> 0.1745Hurt
add sparsity loss Ls and mask supervision loss Lm (ablation)Ours · Real multi-view video dataset (cameras 4,5 input)STRRED: 0.1683 -> 0.1900Hurt
add mask sparsity loss Ls (ablation)Ours · Real multi-view video dataset (cameras 4,5 input)SSIM: 0.8390 -> 0.8393No clear effect
use a 3D mask instead of NeRF-based dynamic methods on two input viewsNSFF/NeRFlow/Non-rigid NeRF · Real multi-view video dataset (cameras 4,5 input)PSNR: 17.0368 -> 26.22Improved
extend to 4 input viewsOurs · qualitativevisual artifactsImproved

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