AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition

Anil S. Baslamisli, Partha Das, Hoàng-Ân Lê, Sezer Karaoğlu, Theo Gevers

IJCV 2021 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 33 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 refinement module fusing branch reflectances (ablation)ShadingNet · NED testSMSE: 0.0030 -> 0.0027Improved
add refinement module fusing branch reflectances (ablation)ShadingNet · GTA VSMSE: 0.0125 -> 0.0124Improved
add refinement module (ablation)ShadingNet · NED testDSSIM: 0.0910 -> 0.0798Improved
explicitly classify shadow casts in a dedicated branch instead of unified shading (ablation)ShadingNet · NED testSMSE: 0.0030 -> 0.0030 (LMSE 0.0157 -> 0.0144)Improved
add fine-grained shading decomposition to ShapeNet backbone (Baseline-a)ShapeNet · NED testSMSE albedo: 0.0075 -> 0.0072Improved
add fine-grained shading decomposition to ShapeNet backbone (Baseline-b)ShapeNet · GTA VSMSE: 0.0138 -> 0.0134No clear effect
use ShadingNet design instead of naive fine-grained baselinesBaseline-a · NED testSMSE albedo: 0.0072 -> 0.0027Improved
use individual decoders (Baseline-b) rather than single unified shading decoder (Baseline-a)fine-grained baselines · NED direct shadingSMSE: 0.0545 -> 0.0579Hurt
use individual decoders (Baseline-b) rather than single unified decoder (Baseline-a)fine-grained baselines · IIW outdoorWHDR: 46.22 -> 39.11Improved
apply guided filter post-processingShadingNet · IIW outdoorWHDR: 35.73 -> 29.98Improved
compare with image-sequence-trained IIDWW using smoothness priorsShadingNet · IIW outdoorWHDR: 21.60 vs 35.73Hurt

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