AI Paper Atlas

Research map / Image generation / Image restoration

Joint Image Filtering with Deep Convolutional Networks

Yijun Li, Jia‐Bin Huang, Narendra Ahuja, Ming–Hsuan Yang

TPAMI 2019 · Image generation › Image restoration · approach: Dehazing and deraining · 204 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 skip connection (residual learning) to the joint filter network (ablation)DJF · NYU v2 depth upsampling 8xRMSE (cm): 6.20 -> 5.86Improved
add skip connection at large filter number n1=256 (ablation)joint filter network · NYU v2 depth upsampling 8xRMSE (cm): 6.40 -> 5.82Improved
increase filter number from n1=64 to n1=256 with skip connection (ablation)joint filter network with skip · NYU v2 depth upsampling 8xRMSE (cm): 5.97 -> 5.82Improved
increase filter number without skip connection (ablation)joint filter network without skip · NYU v2 depth upsampling 8xRMSE (cm): 6.40, 6.44, 6.32, 6.35No clear effect
use multi-channel output features n3=16 instead of n3=1 (ablation)CNN_T and CNN_G with skip · NYU v2 depth upsampling 8xRMSE (cm): 5.86 -> 6.11Hurt
increase filter sizes from f=5/1/3 to f=9/1/5 (ablation)joint filter network with skip · NYU v2 depth upsampling 8xRMSE (cm): 6.24 -> 5.86Improved
enlarge filter size further to f=11/3/7 (ablation)joint filter network with skip · NYU v2 depth upsampling 8xRMSE (cm): 5.86 -> 5.93No clear effect
increase subnetwork depth from d=2 to d=5 (ablation)proposed model · NYU v2 depth upsampling 8xRMSE (cm): 5.99 -> 5.73Improved
deepen a single generic residual network CNN_F_R from d=3 to d=8 (ablation)CNN_F_R · NYU v2 depth upsampling 8xRMSE (cm): 6.31 -> 6.16Improved
add separate target and guidance sub-networks instead of stacking inputs (ablation)proposed model · NYU v2 depth upsampling 8xRMSE (cm): 6.13 -> 5.86Improved
make CNN_F shallower with 4/4-2 depth split (ablation)proposed model · NYU v2 depth upsampling 8xRMSE (cm): 5.86 -> 6.03Hurt
train on RGB/depth instead of RGB/flow (ablation)proposed model · NYU v2 depth upsampling 8xRMSE (cm): 7.32 -> 5.86Improved

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