AI Paper Atlas

Research map / 3D vision / 3D generation

Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images

Philipp Wulff, Felix Wimbauer, Dominik Muhle, Daniel Cremers

ICCV 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 3 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
train the reconstruction model on synthetic single-image geometry instead of multi-view supervisionDream-to-Recon distilled model · KITTI-360IEacc: 0.71 vs BTS 0.69Improved
add depth supervision to BTS baselineBTS · KITTI-360IErec: 0.64 -> 0.66No clear effect
use full conditioning (RGB, depth, mask, CLIP) in the view completion model (ablation)VCM · KITTI-360PSNR: 20.197 -> 23.908Improved
finetune VCM on Waymo (ablation)VCM · WaymoPSNR: 26.963 -> 28.781Improved
use camera rig with 8 poses instead of random orbit with 4 (ablation)scene synthesis · KITTI-360IErec: 0.596 -> 0.729Improved
add depth rendering loss Ldepth (ablation)distillation · KITTI-360IErec: 0.443 -> 0.706Improved
add occupancy loss Locc (ablation)distillation · KITTI-360IEacc: IEacc 0.699 -> 0.705; IErec 0.757 -> 0.706Mixed
add predicted uncertainty to balance losses (ablation)distillation · KITTI-360IEacc: 0.697 -> 0.705Improved
use depth-gradient occlusion detection instead of optical flow (ablation)scene synthesis · KITTI-360occlusion detection quality (qualitative)Improved
distill synthetic scenes into feed-forward modelDream-to-Recon · KITTI-360Oacc: 0.93 -> 0.90Hurt

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