Methods › Computer Vision › Convolutions › Deformable Kernel
Deformable Kernel
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Deformable Kernels is a type of convolutional operator for deformation modeling. DKs learn free-form offsets on kernel coordinates to deform the original kernel space towards specific data modality, rather than recomposing data. This can directly adapt the effective receptive field (ERF) while leaving the receptive field untouched. They can be used as a drop-in replacement of rigid kernels.
As shown in the Figure, for each input patch, a local DK first generates a group of kernel offsets {Δ𝓀} from input feature patch using the light-weight generator 𝒢 (a 3×3 convolution of rigid kernel). Given the original kernel weights 𝒲 and the offset group {Δ𝓀}, DK samples a new set of kernel 𝒲′ using a bilinear sampler ℬ. Finally, DK convolves the input feature map and the sampled kernels to complete the whole computation.
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.
-
RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection 18 Feb 2025 · 0 repositories · arXiv:2502.13071
-
Revisiting Deformable Convolution for Depth Completion 3 Aug 2023 · 2 repositories · arXiv:2308.01905
-
Deformable Kernel Expansion Model for Efficient Arbitrary-shaped Scene Text Detection 28 Mar 2023 · 0 repositories · arXiv:2303.15737
-
H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions 21 Nov 2022 · 0 repositories · arXiv:2211.11309
-
FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition 14 Mar 2022 · 0 repositories · arXiv:2203.07255
-
Deformable Kernel Convolutional Network for Video Extreme Super-Resolution 1 Oct 2020 · 0 repositories · arXiv:2010.00154
-
Deformable Kernel Networks for Joint Image Filtering 17 Oct 2019 · 2 repositories · arXiv:1910.08373
-
Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation 7 Oct 2019 · 2 repositories · arXiv:1910.02940
Tasks archive 2025-07-28
18 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