AI Paper Atlas

Research map / 3D vision / Depth and stereo

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

Junyuan Deng, Wei Yin, Xiaoyang Guo, Qian Zhang, Xiaotao Hu, Weiqiang Ren, Xiao-Xiao Long, Ping Tan

ICCV 2025 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 8 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
add Camera Image representation (with multi-res noise) (ablation)diffusion camera calibration · GSV calibration ablationmean FoV error (deg): 9.10 -> 2.54Improved
add multi-resolution noise (with Camera Image) (ablation)diffusion camera calibration · GSV calibration ablationmean FoV error (deg): 6.72 -> 2.54Improved
add camera image input to metric depth (ablation)diffusion metric depth · NYU-v2delta1: 83.8 -> 85.8Improved
add camera image input to metric depth (ablation)diffusion metric depth · KITTIdelta1: 87.8 -> 89.1Improved
add real data to training (ablation)diffusion metric depth · NYU-v2delta1: 26.5 -> 85.8Improved
use one-step deterministic prediction instead of multi-step denoising (ablation)diffusion metric depth · NYU-v2delta1: 77.1 -> 85.8Improved
train the VAE decoder instead of freezing it (ablation)diffusion metric depth · NYU-v2delta1: 76.7 -> 85.8Improved
train the VAE decoder instead of freezing it (ablation)diffusion metric depth · NYU-v2A.Rel: 48.0 -> 13.5Improved
add camera image to metric depth (ablation)diffusion metric depth · iBims / DIODE indoor / DIODE outdoordelta1: ibims 82.6 -> 88.7; Diode indoor 35.0 -> 50.1; Diode outdoor 25.2 -> 41.0Improved
add camera image to metric depth (ablation)diffusion metric depth · NYU-v2SI_log: 8.0 -> 8.17No clear effect
add estimated intrinsics as cue to sparse-view reconstructionDUSt3R · Relative distance error (4 in-the-wild scenes)relative distance error: Sofa 1.67 -> 1.37; Car 0.87 -> 0.68; Pavilion 1.03 -> 0.68; StoneWall 1.43 -> 1.06Improved
add estimated intrinsics as cue to pose estimationDUSt3R · pose estimation (20 images)t_rel / r_rel: t_rel 1.17 -> 0.63 m; r_rel 5.02 -> 2.30 degImproved

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