AI Paper Atlas

Research map / 3D vision / Face and shape

CNN-Based Real-Time Dense Face Reconstruction with Inverse-Rendered Photo-Realistic Face Images

Yudong Guo, Juyong Zhang, Jianfei Cai, Boyi Jiang, Jianmin Zheng

TPAMI 2018 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 218 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 FineNet on top of Tracking CoarseNet (ablation)Tracking CoarseNet · FaceCap (200 frames, video)average point-to-point distance (mm): 2.11 -> 2.08Improved
add FineNet to CoarseNet on a wrinkle-rich subregion (ablation)CoarseNet · Wrinkle-rich subregion of a video framemean error (mm): 2.20 -> 2.03Improved
use proposed per-pixel projection loss instead of prior CoarseNet loss (ablation)Single-image CoarseNet · AFLW test (~700 images, CoarseNet 15000 iterations)L_pose test error: 26.35 -> 7.69Improved
use proposed per-pixel projection loss instead of prior CoarseNet loss (ablation)Single-image CoarseNet · AFLW test (~700 images, CoarseNet 15000 iterations)L_geo test error: 5.53 -> 4.23Improved
use proposed per-pixel projection loss instead of prior CoarseNet loss (ablation)Single-image CoarseNet · AFLW test (~700 images, CoarseNet 15000 iterations)MSE (pose parameters): 1.91 -> 0.56Improved
use proposed per-pixel projection loss instead of prior CoarseNet loss (ablation)Single-image CoarseNet · AFLW test (~700 images, CoarseNet 15000 iterations)mean vertex distance (geometry parameters): 5.18 -> 4.55Improved
use learned CoarseNet+FineNet instead of optimization-based inverse renderingface reconstruction from video · FaceCap (200 frames, video)average point-to-point distance (mm): 1.81 -> 2.08Mixed
use proposed method instead of the strongest learning-based single-image baselineSingle-image CoarseNet+FineNet · FRGC v2 Spring2004range (2100 images)RMSE (mm): 5.367 -> 4.915Improved
use proposed method instead of the strongest learning-based single-image baselineSingle-image CoarseNet+FineNet · FRGC v2 Spring2004range (2100 images)MAE (mm): 3.923 -> 3.846Improved
use proposed learning-based tracker instead of optimization-based trackerdense face tracking · Video frame with rich details (binocular ground truth)mean error (mm): 1.96 -> 1.8No clear effect
use Tracking CoarseNet with previous-frame pose instead of Single-image CoarseNet on each frame (ablation)video face tracking · Video tracking (qualitative)tracking robustnessImproved
use learned networks instead of optimization-based inverse rendering for single imagessingle-image reconstruction · Large pose and strong lighting images (qualitative)robustnessImproved

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