AI Paper Atlas

Research map / 3D vision / 3D generation

Diffuse3D: Wide-Angle 3D Photography via Bilateral Diffusion

Yutao Jiang, Yang Zhou, Yuan Liang, Wenxi Liu, Jianbo Jiao, Yuhui Quan, Shengfeng He

ICCV 2023 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 10 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 spatial denoising kernel with depth-aware bilateral kernel (ablation)Diffuse3D · RealEstate-10K (entire scene)PSNR: 19.83 -> 20.72Improved
add local context inpainting branch (ablation)Diffuse3D · RealEstate-10K (entire scene)PSNR: 20.02 -> 20.72Improved
add global context inpainting branch (ablation)Diffuse3D · RealEstate-10K (entire scene)PSNR: 20.32 -> 20.72Improved
inject depth kernel in both input and output blocks rather than one (ablation)Diffuse3D · RealEstate-10K (entire scene)PSNR: 20.41 -> 20.72Improved
bilateral diffusion vs AdaMPI on pixel metricsDiffuse3D · RealEstate-10K (entire scene)PSNR: 20.72 vs 22.57Hurt
bilateral diffusion inpainting vs 3D Photo inpainting3D Photo LDI pipeline · RealEstate-10K (entire scene)LPIPS: 0.153 -> 0.132Improved

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