AI Paper Atlas

Research map / 3D vision / Face and shape

Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images

Tianhao Wu, Chuanxia Zheng, Frank Guan, Andrea Vedaldi, Tat-Jen Cham

ICCV 2025 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 48 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
replace naive token concatenation with mask-weighted attention plus occlusion-aware layer (full model) (ablation)Amodal3R · GSO single-viewFID: 31.96 -> 30.64Improved
replace naive token concatenation with mask-weighted attention plus occlusion-aware layer (full model) (ablation)Amodal3R · GSO single-viewKID (%): 0.49 -> 0.35Improved
add occlusion-aware layer to mask-weighted attention (ablation)Amodal3R · GSO single-viewCOV (%): 36.90 -> 39.61Improved
add occlusion-aware layer to mask-weighted attention (ablation)Amodal3R · GSO single-viewMMD: 3.69 -> 3.62Improved
add mask-weighted attention to occlusion-aware layer (ablation)Amodal3R · GSO single-viewKID (%): 0.57 -> 0.35Improved
add mask-weighted attention to occlusion-aware layer (ablation)Amodal3R · GSO single-viewCOV (%): 40.19 -> 39.61Hurt
use 4 occluded views instead of 1 viewAmodal3R · GSOFID: 30.64 -> 26.27Improved
use 4 independently pix2gestalt-completed views instead of 1 completed viewTRELLIS · GSOFID: 58.82 -> 65.69Hurt
use 4 views completed by pix2gestalt+MV instead of 1 completed viewTRELLIS · GSOKID (%): 5.87 -> 1.85Improved
use single-stage Amodal3R instead of pix2gestalt + TRELLISTRELLIS · Toys4K single-viewFID: 43.05 -> 23.45Improved

Later papers that compared with this method

3 later accepted papers report Amodal3R as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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