AI Paper Atlas

Research map / 3D vision / 3D generation

Single-View View Synthesis with Self-rectified Pseudo-Stereo

Yang Zhou, Hanjie Wu, Wenxi Liu, Zheng Xiong, Jing Qin, Shengfeng He

IJCV 2023 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 8 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 bidirectional matching rectification (ablation)baseline warping · KITTI stereo synthesisPSNR: 20.1 -> 21.3Improved
add pruning-based rectification (ablation)baseline warping · KITTI stereo synthesisPSNR: 20.1 -> 21.0Improved
combine pruning and bidirectional matching rectification (ablation)baseline warping · KITTI stereo synthesisPSNR: 20.1 -> 22.1Improved
combine pruning and bidirectional matching rectification (ablation)baseline warping · KITTI stereo synthesisLPIPS: 0.161 -> 0.124Improved
raise pruning percentage from 10% to 50% (ablation)pruning rectification · KITTI stereo synthesisPSNR: 21.5 -> 22.1Improved
raise pruning percentage from 50% to 90% (ablation)pruning rectification · KITTI stereo synthesisPSNR: 22.1 -> 21.6Hurt
use 3D convolution instead of 2D CNN for MPI reconstruction (ablation)Ours · KITTI MPI novel view synthesisPSNR: 22.0 -> 22.6Improved
add pseudo-stereo input to single-view MPI prediction (ablation)MINE · KITTI MPI novel view synthesisPSNR: 21.4 -> 22.6Improved
use real stereo pairs instead of pseudo-stereoOurs · KITTI MPI novel view synthesisPSNR: 22.6 -> 30.7Improved
add pseudo-stereo input to LDI prediction (ablation)Tulsiani et al. · KITTI LDI novel view synthesisPSNR: 16.5 -> 18.6Improved
add pseudo-stereo input to MPI prediction (ablation)MINE · Scene Flow novel view synthesisPSNR: 15.7 -> 17.0Improved
add pseudo-stereo input to MPI predictionMINE · Flowers Light FieldsPSNR: 30.2 -> 30.5Improved

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