AI Paper Atlas

Research map / 3D vision / 3D generation

Content-Aware Warping for View Synthesis

Mantang Guo, Junhui Hou, Jing Jin, Hui Liu, Huanqiang Zeng, Jiwen Lu

TPAMI 2023 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 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 content embedding (ablation)base view synthesis model · DTU (2 inputs)average PSNR (dB): 20.69 -> 21.85Improved
add global embedding (ablation)content-aware warping model · DTU (2 inputs)average PSNR (dB): 21.85 -> 21.94Improved
add adaptive PSV fusion (ablation)content-aware warping model · DTU (2 inputs)average PSNR (dB): 21.94 -> 22.15Improved
add feature-space warping (ablation)content-aware warping model · DTU (2 inputs)average PSNR (dB): 22.15 -> 22.30Improved
add weight-smoothness loss (ablation)content-aware warping model · DTU (2 inputs)average PSNR (dB): 22.30 -> 22.41Improved
replace disparity-based warping with content-aware warpingBaseline (Warp) · Inria Sparse LFaverage PSNR (dB): 28.27 -> 31.00Improved
add more accurate disparity input to Jin et al.Jin et al. · Inria Sparse LFaverage PSNR (dB): 27.54 -> 29.00Improved
use new components over preliminary versionGuo et al. · Inria Sparse LFaverage PSNR (dB): 30.17 -> 31.00Improved
use new components over preliminary versionGuo et al. · DTUaverage PSNR (dB): 20.29 -> 22.41Improved
increase source views from 2 to 3content-aware warping model · DTUaverage PSNR (dB): 22.41 -> 23.27Improved
increase source views from 3 to 4content-aware warping model · DTUaverage PSNR (dB): 23.27 -> 23.72Improved
content-aware warping vs IBRNet and SVNVS on texture-less scenescontent-aware warping model · DTU scan66/67/106PSNR: scan66 23.57 vs IBRNet 25.09Hurt

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