AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Appearance Maps

Maxim Maximov, Laura Leal-Taixe, Mario Fritz, Tobias Ritschel

ICCV 2019 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 32 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
represent appearance as a 4D deep appearance map instead of multi-view reflectance map RM++DAM · Synthetic point light, novel viewDSSIM: .181 -> .144Improved
represent appearance as a 4D deep appearance map instead of multi-view reflectance map RM++DAM · Synthetic environment map, novel viewDSSIM: .193 -> .164Improved
represent appearance as a 4D deep appearance map instead of RM++DAM · Synthetic point light, same viewDSSIM: .143 -> .105Improved
represent appearance as a 4D deep appearance map instead of RM++DAM · Synthetic environment map, same viewDSSIM: .160 -> .123Improved
replace per-material SGD fitting with a learning-to-learn network predicting DAM weightsDAM · Synthetic point light, novel viewDSSIM: .144 -> .165Hurt
replace per-material SGD fitting with a learning-to-learn network predicting DAM weightsDAM · Synthetic environment map, novel viewDSSIM: .164 -> .173Hurt
replace per-material SGD fitting with a learning-to-learn networkDAM · Synthetic environment map, same viewDSSIM: .123 -> .131Hurt
replace per-material SGD fitting with a learning-to-learn networkDAM · Synthetic point light, same viewDSSIM: .105 -> .106No clear effect
use joint estimation-and-segmentation instead of k-means segmentation then per-segment estimationDAM · MultiMaterial point light, novel viewDSSIM: .172 -> .161Improved
use joint estimation-and-segmentation instead of k-means segmentationDAM · MultiMaterial environment map, novel viewDSSIM: .164 -> .154Improved
use joint estimation-and-segmentation instead of k-means segmentationDAM · MultiMaterial point light, same viewDSSIM: .132 -> .113Improved
use joint estimation-and-segmentation instead of k-means segmentationDAM · MultiMaterial environment map, same viewDSSIM: .136 -> .122Improved

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