AI Paper Atlas

Research map / 3D vision / Depth and stereo

Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence

Panagiotis P. Filntisis, George Retsinas, Radek Danecek, Vanessa Sklyarova, Petros Maragos, Timo Bolkart

CVPR 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 1 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
train without precomputed registrations (MOCHI vs TEMPEH trained with registrations)TEMPEH · FaMoS testmedian point-to-surface error (mm): 0.36 -> 0.26Improved
zero-shot transfer to CoMA (MOCHI vs TEMPEH)TEMPEH · CoMA zero-shotmedian point-to-surface error (mm): 0.81 -> 0.53Improved
add test-time optimization (50 iterations) with scanMOCHI · FaMoS testmedian point-to-surface error (mm): 0.26 -> 0.07Improved
MOCHI TTO instead of classic registration pipelineClassic Registrations · FaMoS testmedian point-to-surface error (mm): 0.10 -> 0.07Improved
increase TTO iterations from 20 to 100 (ablation)MOCHI TTO · FaMoS valmedian point-to-surface error (mm): 0.08 -> 0.06Improved
use point-map and normal losses instead of point-to-surface loss in TTO (ablation)MOCHI TTO · FaMoS valmedian point-to-surface error (mm): 0.10 -> 0.08 at t=20; 0.06 -> 0.06 at t=100Mixed
use point-map losses instead of point-to-surface in coarse stage training (ablation)MOCHI coarse stage · FaMoSvisual artifacts / self-intersectionsImproved
add normal-map loss in TTO (ablation)MOCHI TTO · FaMoS valmedian point-to-surface error (mm): 0.09 -> 0.08Improved
add pretrained weights before TTO (vs optimizing from random initialization) (ablation)MOCHI TTO · FaMoS valmedian point-to-surface error (mm): 0.44 -> 0.07Improved
optimize refinement module weights instead of vertices directly (ablation)MOCHI TTO · FaMoS valmedian point-to-surface error (mm): 0.09 -> 0.07Improved
add PLIKS inverse parameter recovery on top of 2D landmarks (ablation)MOCHI · FaMoSmesh topology quality (qualitative)Improved
add dense 2D landmark supervision to point-map loss plus PLIKS (ablation)MOCHI · FaMoSlip and eye alignment (qualitative)Improved

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