AI Paper Atlas

Research map / 3D vision / Face and shape

Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modeling

Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien Dai Bui

IJCV 2018 · 3D vision › Face and shape · approach: 3D morphable face model regression · 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
use DAMs reconstruction instead of bicubic/AAMsface super-resolution · LFPW (alpha=16)RMSE: 19.74 -> 19.24Improved
use DAMs instead of AAMsface super-resolution · Helen (alpha=16)RMSE: 22.3 -> 21.24Improved
use DAMs instead of AAMsface super-resolution · LFPW (alpha=8)PSNR (dB): 24.82 -> 25.06Improved
use DAMs instead of AAMs at small magnificationface super-resolution · Helen (alpha=4)PSNR (dB): 26.56 -> 26.54No clear effect
use DAMs frontalization instead of LFW3DPittpatt on LFW · LFW verificationaccuracy (%): 86.63% -> 87.72%Improved
use DAMs instead of PCA-based AAMsocclusion removal reconstruction · AR occluded subsetRMSE vs neutral faces: 47.36 -> 45.08Improved
use DAMs instead of RoBMocclusion recognition · AR sunglassesrank-1 (%): 71.89% -> 76.87%Improved
use DAMs instead of AAMs under impulsive noiseage estimation on reconstructed faces · FG-NET (noise range 25)MAE (years): 6.15 -> 5.81Improved
use DAMs instead of AAMs for low-resolution facesage estimation · FG-NET (alpha=8)MAE (years): 6.69 -> 6.21Improved
use DAMs model parameters as features instead of AAMsage estimation · FG-NETMAE (years): 4.81 -> 4.67Improved
use DAMs model parameters instead of reconstructed imageage estimation · FG-NETMAE (years): 5.67 -> 4.67Improved
use DAMs instead of AAMs for shape fitting (HoG/Dense SIFT AAMs as reference)landmark fitting · LFPWfitting error: 0.0398 vs 0.0372 (HoG AAMs), 0.035 (Dense SIFT AAMs)Mixed

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