AI Paper Atlas

Research map / 3D vision / 3D generation

Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition

Raza Yunus, Benjamin Ummenhofer, Jan Eric Lenssen, Eddy Ilg

ECCV 2026 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 0 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
capture rigid hand-held motion instead of static dome (estimated poses)Ours · Synthetic diffuse materialsalbedo PSNR (dB): 32.68 -> 40.33Improved
hand-held capture instead of static domeOurs · Synthetic original materialsrelighting PSNR (dB): 38.14 -> 40.24Improved
hand-held rotations instead of single-axis turntableOurs · Synthetic diffuse materialsalbedo PSNR (dB): 35.65 -> 40.55Improved
turntable instead of static dome (GT poses)Ours · Synthetic original materialsalbedo PSNR (dB): 36.72 -> 36.15Hurt
use estimated instead of ground-truth poses in hand-held settingOurs · Synthetic diffuse materialsalbedo PSNR (dB): 40.55 -> 40.33No clear effect
our pipeline vs IRGS in static settingOurs · TensoIR syntheticalbedo PSNR (dB): 33.41 -> 33.96Improved
our pipeline vs IRGS in static settingOurs · TensoIR syntheticnormal MAE (deg): 3.99 -> 4.19Hurt
our SDF-based Gaussian pipeline vs extended IRGS on hand-held sequencesOurs · Hand-held sequencesrelighting PSNR (dB): 32.99 -> 39.65Improved
share more frames per environment map in ReCap baseline (ablation)ReCap · Hand-held sequencesalbedo PSNR (dB): 21.91 -> 22.42 (10 vs 40 envs)No clear effect
3D Gaussian refinement with better matcher vs FMOVOurs · HO3DAUC ATE: 31.19 -> 35.26Improved
hand-held views instead of more static views (25 vs 400) (ablation)Ours · syntheticdecomposition qualityImproved
uniform white lighting for hand-held capture (ablation)Ours · syntheticalbedo qualityNo clear effect

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