AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features

Junbo Ke, Yangyang Xu, Chao Wang, You-Wei Wen

CVPR 2026 · Architectures and efficiency › RNNs and normalization · approach: Sparse dictionary representations · 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
add CAFE parallel linear layers with Hadamard product to RFF (ablation)RFF MLP · 2D image fitting D2K0PSNR (dB): 26.18 -> 34.87Improved
add Chebyshev features to RFF (ablation)RFF MLP · 2D image fitting D2K0PSNR (dB): 26.18 -> 33.00Improved
add Chebyshev features to CAFE (ablation)CAFE · 2D image fitting D2K0PSNR (dB): 34.87 -> 39.47Improved
add Chebyshev features to CAFE (ablation)CAFE · 2D image fitting D2K1PSNR (dB): 37.36 -> 44.34Improved
add CAFE to Chebyshev+Fourier features (ablation)Fourier-Chebyshev MLP · 2D image fitting D2K2PSNR (dB): 35.60 -> 44.18Improved
increase number of parallel linear layers (ablation)CAFE+ · 2D image fitting (DIV1)PSNR (dB): steady gain then saturation (figure only)Improved
remove backbone MLP (0 layers vs 2) (ablation)CAFE+ · 2D image fitting D2K5-D2K7Avg PSNR (dB): 42.26 -> 35.56Hurt
increase backbone MLP depth beyond 2 layers (ablation)CAFE+ · 2D image fitting D2K5-D2K7Avg PSNR (dB): 42.26 -> 42.17 (3), 42.52 (4)No clear effect
increase depth of plain RFF MLP instead of encoding layers (ablation)RFF · image fittingPSNR (dB)No clear effect
CAFE+ vs FINER on DrumsCAFE+ · NeRF Blender DrumsPSNR (dB): 25.66 -> 25.59No clear effect
CAFE+ vs FINER on ShipCAFE+ · NeRF Blender ShipPSNR (dB): 22.02 -> 23.12Improved
CAFE+ default vs SL2A on D2K5CAFE+ (default) · 2D image fitting D2K5PSNR (dB): 37.03 -> 36.64Hurt

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