AI Paper Atlas

Research map / 3D vision / 3D generation

Reflection-aware generative novel view synthesis

GeonU Kim, Shin Dong-Yeon, Tae-Hyun Oh

ECCV 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 0 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 Ref-GeNVS reflection-aware generationMVGenMaster · Synthetic sparse-input, full scenePSNR: 16.90 -> 17.95Improved
add Ref-GeNVS reflection-aware generationSEVA · Synthetic sparse-input, full scenePSNR: 13.65 -> 15.51Improved
add Ref-GeNVSMVGenMaster · Synthetic sparse-input, reflected regionPSNR: 16.51 -> 18.40Improved
add Ref-GeNVSSEVA · Synthetic sparse-input, reflected regionPSNR: 13.31 -> 16.11Improved
add Ref-GeNVSMVGenMaster · Synthetic sparse-input, mirror surfacePSNR: 19.41 -> 19.69Improved
add Ref-GeNVSSEVA · Synthetic sparse-input, mirror surfacePSNR: 15.25 -> 16.16Improved
use mirror-masked surface-point plane estimation instead of edge-based estimation (ablation)Ref-GeNVS · Synthetic data with corrupted mirror masksDreamSim, LPIPS, CLIP, PSNRImproved
add Ref-GeNVS two-stage pipeline (extra preprocessing and generation)SEVA · Sparse-view NVSinference time: 130 -> 397Hurt

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