Methods › Computer Vision › Image Model Blocks › Spatial Feature Transform
Spatial Feature Transform
Introduced by Xintao Wang et al. in Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Spatial Feature Transform, or SFT, is a layer that generates affine transformation parameters for spatial-wise feature modulation, and was originally proposed within the context of image super-resolution. A Spatial Feature Transform (SFT) layer learns a mapping function ℳ that outputs a modulation parameter pair (γ, β) based on some prior condition Ψ. The learned parameter pair adaptively influences the outputs by applying an affine transformation spatially to each intermediate feature maps in an SR network. During testing, only a single forward pass is needed to generate the HR image given the LR input and segmentation probability maps.
More precisely, the prior Ψ is modeled by a pair of affine transformation parameters (γ, β) through a mapping function ℳ: Ψ↦(γ, β). Consequently,
𝐲̂=G_θ(𝐱 |γ, β), (γ, β)=ℳ(Ψ)
After obtaining (γ, β) from conditions, the transformation is carried out by scaling and shifting feature maps of a specific layer:
SFT(𝐅 |γ, β)=γ ⊙𝐅+β
where 𝐅 denotes the feature maps, whose dimension is the same as γ and β, and ⊙ is referred to element-wise multiplication, i.e., Hadamard product. Since the spatial dimensions are preserved, the SFT layer not only performs feature-wise manipulation but also spatial-wise transformation.
Papers archive 2025-07-28
8 shown of 8, 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.
-
JAFAR: Jack up Any Feature at Any Resolution 10 Jun 2025 · 1 repository · arXiv:2506.11136
-
HeightLane: BEV Heightmap guided 3D Lane Detection 15 Aug 2024 · 0 repositories · arXiv:2408.08270
-
Arc2Face: A Foundation Model for ID-Consistent Human Faces 18 Mar 2024 · 3 repositories · arXiv:2403.11641Syntology ran 1 of 4 samples · 3 unverified · 3 pointer-only (licence)
-
Boosting Cross-Quality Face Verification using Blind Face Restoration 15 Aug 2023 · 0 repositories · arXiv:2308.07967
-
Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform 21 Aug 2021 · 1 repository · arXiv:2108.09551Syntology ran 14 of 23 samples · 9 unverified · 23 pointer-only (licence)
-
Towards Real-World Blind Face Restoration with Generative Facial Prior 11 Jan 2021 · 1 repository · arXiv:2101.04061
-
Blind Super-Resolution With Iterative Kernel Correction 6 Apr 2019 · 3 repositories · arXiv:1904.03377Syntology ran 2 of 6 samples · 4 unverified
-
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform 9 Apr 2018 · 4 repositories · arXiv:1804.02815
Tasks archive 2025-07-28
17 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