Methods › General › Normalization › SPADE
Spatially-Adaptive Normalization
SPADE
Introduced by Taesung Park et al. in Semantic Image Synthesis with Spatially-Adaptive Normalization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SPADE, or Spatially-Adaptive Normalization is a conditional normalization method for semantic image synthesis. Similar to Batch Normalization, the activation is normalized in the channel-wise manner and then modulated with learned scale and bias. In the SPADE, the mask is first projected onto an embedding space and then convolved to produce the modulation parameters γ and β. Unlike prior conditional normalization methods, γ and β are not vectors, but tensors with spatial dimensions. The produced γ and β are multiplied and added to the normalized activation element-wise.
Papers archive 2025-07-28
30 shown of 38, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning 8 Jul 2025 · 0 repositories · arXiv:2507.05798
-
SPADE: Spectroscopic Photoacoustic Denoising using an Analytical and Data-free Enhancement Framework 16 Dec 2024 · 0 repositories · arXiv:2412.12068
-
♠ SPADE ♠ Split Peak Attention DEcomposition 6 Nov 2024 · 0 repositories · arXiv:2411.05852
-
Guided Synthesis of Labeled Brain MRI Data Using Latent Diffusion Models for Segmentation of Enlarged Ventricles 2 Nov 2024 · 0 repositories · arXiv:2411.01351
-
SVS-GAN: Leveraging GANs for Semantic Video Synthesis 9 Sep 2024 · 0 repositories · arXiv:2409.06074
-
All-day Depth Completion 27 May 2024 · 0 repositories · arXiv:2405.17315
-
Controllable Face Synthesis with Semantic Latent Diffusion Models 19 Mar 2024 · 2 repositories · arXiv:2403.12743
-
Synthesizing Traffic Datasets using Graph Neural Networks 8 Dec 2023 · 1 repository · arXiv:2312.05031
-
Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning 3 Nov 2023 · 1 repository · arXiv:2311.02003
-
SPADE: Sparsity-Guided Debugging for Deep Neural Networks 6 Oct 2023 · 1 repository · arXiv:2310.04519Syntology ran 5 of 9 samples · 4 unverified · 9 pointer-only (licence)
-
Semantic Image Synthesis via Class-Adaptive Cross-Attention 30 Aug 2023 · 2 repositories · arXiv:2308.16071
-
SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving 12 May 2023 · 0 repositories · arXiv:2305.07522
-
ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review 13 Apr 2023 · 0 repositories · arXiv:2305.03123
-
Efficient Long Sequence Modeling via State Space Augmented Transformer 15 Dec 2022 · 1 repository · arXiv:2212.08136Syntology ran 3 of 5 samples · 2 unverified
-
SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch 30 Nov 2022 · 0 repositories · arXiv:2212.00173
-
Keep Your Friends Close & Enemies Farther: Debiasing Contrastive Learning with Spatial Priors in 3D Radiology Images 16 Nov 2022 · 0 repositories · arXiv:2211.08643
-
Synthesis of realistic fetal MRI with conditional Generative Adversarial Networks 20 Sep 2022 · 0 repositories · arXiv:2209.09696
-
Context-Consistent Semantic Image Editing with Style-Preserved Modulation 13 Jul 2022 · 1 repository · arXiv:2207.06252
-
MultiEarth 2022 -- The Champion Solution for Image-to-Image Translation Challenge via Generation Models 17 Jun 2022 · 0 repositories · arXiv:2207.00001
-
Anomaly Detection in Retinal Images using Multi-Scale Deep Feature Sparse Coding 27 Jan 2022 · 0 repositories · arXiv:2201.11506
-
Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation 11 Oct 2021 · 1 repository · arXiv:2110.05055
-
USIS: Unsupervised Semantic Image Synthesis 29 Sep 2021 · 1 repository · arXiv:2109.14715
-
3D Human Shape Style Transfer 3 Sep 2021 · 0 repositories · arXiv:2109.01587
-
UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing 12 Aug 2021 · 0 repositories · arXiv:2108.05650
-
PD-GAN: Probabilistic Diverse GAN for Image Inpainting 5 May 2021 · 1 repository · arXiv:2105.02201Syntology ran 1 of 5 samples · 4 unverified
-
DeFLOCNet: Deep Image Editing via Flexible Low-level Controls 23 Mar 2021 · 1 repository · arXiv:2103.12723Syntology ran 5 of 9 samples · 4 unverified
-
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation 7 Feb 2021 · 2 repositories · arXiv:2102.03716
-
Focal Frequency Loss for Image Reconstruction and Synthesis 23 Dec 2020 · 1 repository · arXiv:2012.12821
-
Efficient Semantic Image Synthesis via Class-Adaptive Normalization 8 Dec 2020 · 1 repository · arXiv:2012.04644
-
Low Bandwidth Video-Chat Compression using Deep Generative Models 1 Dec 2020 · 0 repositories · arXiv:2012.00328
Tasks archive 2025-07-28
20 shown of 68 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections