AI Paper Atlas

Research map / 3D vision / 3D generation

Zero-Shot Novel Depth Synthesis Using Foundation Models Scene Representations

Denis Akola, David Fouhey

ECCV 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images

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
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-VGGT · In-domain (1 source -> 1 target)AbsRel: 0.098 -> 0.076Improved
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-WM · In-domain (1 source -> 1 target)AbsRel: 0.108 -> 0.075Improved
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-VGGT · In-domain (2 sources -> 4 targets)AbsRel: 0.248 -> 0.112Improved
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-WM · In-domain (2 sources -> 4 targets)AbsRel: 0.215 -> 0.118Improved
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-VGGT · MegaDepth (2 sources -> 4 targets)AbsRel: 0.102 -> 0.039Improved
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-VGGT · DTU (1 source -> 1 target)AbsRel: 0.022 -> 0.012Improved
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-VGGT · NRGBD (1 source -> 1 target)AbsRel: 0.192 -> 0.260Hurt
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-WM · NRGBD (1 source -> 1 target)AbsRel: 0.127 -> 0.133No clear effect
diffuse in 3DFM latent space instead of depth space (ablation)Z3D-VGGT · 7-Scenes (2 sources -> 4 targets)AbsRel: 0.372 -> 0.342Improved
use Z3D latent diffusion instead of LVSM plus 3DFM depthZ3D-VGGT · DTU (1 source -> 1 target)AbsRel: 0.468 -> 0.012Improved
use Z3D instead of LVSM plus 3DFMZ3D-WM · NRGBD (2 sources -> 4 targets)AbsRel: 0.121 -> 0.131Mixed
linear probe 3DFM features for layered depthVGGT features · LDI predictionAbsRel: 0.319 -> 0.197Improved

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