AI Paper Atlas

Research map / 3D vision / 3D generation

LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis

Stanislaw Szymanowicz, Minghao Chen, Jianyuan Wang, Christian Rupprecht, Andrea Vedaldi

CVPR 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 4 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
initialize encoder from VGGT (3D-aware) instead of training from scratch (ablation)LagerNVS highway encoder-decoder · DL3DV 2-view, known camerasPSNR: 18.03 -> 21.02Improved
initialize from DinoV2 (2D pre-training) instead of scratch (ablation)LagerNVS highway encoder-decoder · DL3DV 2-view, known camerasPSNR: 18.03 -> 18.17Improved
fine-tune the whole VGGT encoder end-to-end instead of freezing it (ablation)LagerNVS · DL3DV 2-view, known camerasPSNR: 19.01 -> 21.02Improved
use highway encoder-decoder instead of decoder-only (ablation)NVS architecture · DL3DV 2-view, known camerasPSNR: 18.39 -> 21.02Improved
use highway encoder-decoder instead of bottleneck encoder-decoder (ablation)NVS architecture · DL3DV 2-view, known camerasPSNR: 17.53 -> 21.02Improved
use full attention decoder instead of cross-attention decoder (ablation)LagerNVS · RealEstate10k 2-view (batch 512)PSNR: 31.06 -> 31.39Improved
use cross-attention decoder instead of full attention (speed trade-off) (ablation)LagerNVS · DL3DV 2-view, known camerasPSNR: 21.02 -> 21.30Mixed
replace LVSM with LagerNVS highway encoder-decoderRealEstate10k 2-view, batch 512 · RealEstate10kPSNR: 29.67 -> 31.39Improved
replace explicit 3DGS (DepthSplat) with latent 3D representationDL3DV 4-view with cameras · DL3DV 4-viewPSNR: 22.30 -> 27.56Improved
replace AnySplat with LagerNVS on CO3D without camerasCO3D 9-view · CO3D 9-viewPSNR: 15.87 -> 22.37Improved
fine-tune decoder with diffusion objective (frozen encoder)LagerNVS · occlusion and extrapolation (qualitative)visual qualityImproved

Later papers that compared with this method

1 later accepted paper reports LagerNVS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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