AI Paper Atlas

Research map / 3D vision / 3D generation

LaRP: Efficient Multi-View Inpainting with Latent Reprojection Priors

Gaoyang Zhang, Xinguo Liu

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis

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 LaRP latent reprojection instead of ControlNet on reprojected pixels (ablation)LaRP · SPIn-NeRFFID: 40.12 -> 34.84Improved
use LaRP conditioning instead of cross-attention (ablation)LaRP · SPIn-NeRFMEt3R (MASt3R): 0.1735 -> 0.1109Improved
keep UNet decoder locked instead of unlocking it (ablation)LaRP · SPIn-NeRFFID: 37.18 -> 34.84Improved
train on two-view data instead of single-view CC12M (ablation)LaRP · SPIn-NeRFFID: 44.15 -> 34.84Improved
add latent dropout to single-view training (ablation)LaRP · SPIn-NeRFFID: 44.15 -> 43.29No clear effect
add FPS-based view selection (ablation)LaRP · SPIn-NeRFFID: 36.19 -> 34.84Improved
add 3D-aware mask preparation (ablation)LaRP · SPIn-NeRFLPIPS: 0.2789 -> 0.2458Improved
train on all object categories instead of single category (ablation)LaRP · SPIn-NeRFFID: 35.02 -> 34.84No clear effect
use LaRP cloned-encoder design instead of ControlNet (ablation)LaRP · training convergencesteps to sudden convergence: ~7,000 -> ~2,000 stepsImproved
use LaRP instead of MVInpainter-F for training costLaRP · trainingtotal training time: 3 days -> 14 hoursImproved
use LaRP+NeRF 20 min instead of MALD-NeRF 960 minLaRP · SPIn-NeRFtime: 960 min -> 20 minImproved
use LaRP inpaintings with 4 min NeRF training instead of 20 min (ablation)LaRP · SPIn-NeRFLPIPS: 0.2458 -> 0.3006Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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