AI Paper Atlas

Research map / 3D vision / Face and shape

Efficient Unrolled Networks for Large-Scale 3D Inverse Problems

Romain Vo, Julián Tachella

CVPR 2026 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 2 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 domain partitioning (patch training) to unrolled 3D network (ablation)Unrolled[3D] · Calgary MC-MRIpeak VRAM (GB): 75.93 -> 37.02Improved
add domain partitioning to unrolled 3D network (ablation)Unrolled[3D] · Calgary MC-MRIPSNR (dB): 36.23 -> 35.85Hurt
add domain partitioning to unrolled 3D network (ablation)Unrolled[3D] · Walnut-CBCTtrainability: OOM -> 34.11 PSNRImproved
add normal operator approximation on top of domain partitioning (ablation)Unrolled[3D] · Walnut-CBCTtrain s/step: 1.65 x4 -> 1.21 x4Improved
add normal operator approximation on top of domain partitioning (ablation)Unrolled[3D] · Walnut-CBCTPSNR (dB): 34.11 -> 34.15Improved
add normal operator approximation alone (ablation)Unrolled[3D] · Calgary MC-MRIPSNR (dB): 36.23 -> 35.12Hurt
add normal operator approximation on top of domain partitioning (ablation)Unrolled[3D] · Calgary MC-MRIPSNR (dB): 35.85 -> 35.09Hurt
add normal operator approximation on top of domain partitioning (ablation)Unrolled[3D] · Calgary MC-MRItrain s/step: 1.10 -> 1.09No clear effect
replace exact normal operator with diagonal-circulant approximation in data stepdata-consistency step · Walnut-CBCT [8x384x384]steps per second: 4.19 -> 12.5Improved
replace exact normal operator with approximation in data stepdata-consistency step · MC-MRI [8x128x128]steps per second: 357 -> 472Improved
add second test-time refinement step with ground-truth-free contextdomain-partitioned network · Walnut-CBCTreconstruction qualityImproved
add second test-time refinement stepdomain-partitioned network · Calgary MC-MRIreconstruction qualityNo clear effect

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