AI Paper Atlas

Research map / 3D vision / Depth and stereo

Neural Kaleidoscopic Space Sculpting

Byeongjoo Ahn, Michael De Zeeuw, Ioannis Gkioulekas, Aswin C. Sankaranarayanan

CVPR 2023 · 3D vision › Depth and stereo · approach: Neural light field and illumination imaging · 3 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 the texture constraint to the silhouette-only method (ablation)Neural kaleidoscopic space sculpting · Simulated armadillochamfer: 5.53 -> 2.56Improved
add the visual hull constraint to the silhouette-only method (ablation)Neural kaleidoscopic space sculpting · Simulated armadillochamfer: 5.53 -> 6.22Hurt
add the visual hull constraint when texture is already used (ablation)Neural kaleidoscopic space sculpting · Simulated armadillochamfer: 2.56 -> 1.87Improved
use texture information from foreground pixels with silhouette sculpting (ablation)Neural kaleidoscopic space sculpting · Real objectsPSNRImproved
add the visual hull constraint to silhouette and texture sculpting (ablation)Neural kaleidoscopic space sculpting · Real chairmask errorImproved
use the proposed full method instead of IDR with visual-hull labels from all raysSimulated armadillo reconstruction · Simulated armadillochamfer: 4.42 -> 1.87Improved

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