Methods › Computer Vision › RoI Feature Extractors › RoIAlign
RoIAlign
Introduced by Kaiming He et al. in Mask R-CNN
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh quantization of RoI Pool, properly aligning the extracted features with the input. To avoid any quantization of the RoI boundaries or bins (using x/16 instead of [x/16]), RoIAlign uses bilinear interpolation to compute the exact values of the input features at four regularly sampled locations in each RoI bin, and the result is then aggregated (using max or average).
Papers archive 2025-07-28
30 shown of 611, 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.
-
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing 20 Jun 2025 · 0 repositories · arXiv:2506.17450
-
A novel visual data-based diagnostic approach for estimation of regime transition in pool boiling 12 Jun 2025 · 0 repositories · arXiv:2506.10832
-
Bringing SAM to new heights: Leveraging elevation data for tree crown segmentation from drone imagery 5 Jun 2025 · 0 repositories · arXiv:2506.04970
-
Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy 4 Jun 2025 · 0 repositories · arXiv:2506.04381
-
Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing 29 May 2025 · 1 repository · arXiv:2505.23134
-
Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals 26 May 2025 · 0 repositories · arXiv:2505.19386
-
OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blender 26 May 2025 · 1 repository · arXiv:2505.20126
-
Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting 22 May 2025 · 0 repositories · arXiv:2505.16513
-
SurgPose: Generalisable Surgical Instrument Pose Estimation using Zero-Shot Learning and Stereo Vision 16 May 2025 · 0 repositories · arXiv:2505.11439
-
KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification 8 May 2025 · 1 repository · arXiv:2505.05583
-
DARTer: Dynamic Adaptive Representation Tracker for Nighttime UAV Tracking 1 May 2025 · 0 repositories · arXiv:2505.00752
-
A Robust Deep Networks based Multi-Object MultiCamera Tracking System for City Scale Traffic 1 May 2025 · 0 repositories · arXiv:2505.00534
-
Transcending Dimensions using Generative AI: Real-Time 3D Model Generation in Augmented Reality 27 Apr 2025 · 0 repositories · arXiv:2504.21033
-
Learning Underwater Active Perception in Simulation 23 Apr 2025 · 0 repositories · arXiv:2504.17817
-
Real-time Seafloor Segmentation and Mapping 14 Apr 2025 · 0 repositories · arXiv:2504.10750
-
From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes 7 Apr 2025 · 0 repositories · arXiv:2504.04827
-
BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing 2 Apr 2025 · 1 repository · arXiv:2504.01786
-
RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety 1 Apr 2025 · 0 repositories · arXiv:2504.01128
-
AI-Assisted Colonoscopy: Polyp Detection and Segmentation using Foundation Models 31 Mar 2025 · 1 repository · arXiv:2503.24138
-
Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery 26 Mar 2025 · 0 repositories · arXiv:2503.20199
-
TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection 18 Mar 2025 · 0 repositories · arXiv:2503.13903
-
YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction 18 Mar 2025 · 0 repositories · arXiv:2503.13883
-
DivCon-NeRF: Generating Augmented Rays with Diversity and Consistency for Few-shot View Synthesis 17 Mar 2025 · 0 repositories · arXiv:2503.12947
-
Securing Virtual Reality Experiences: Unveiling and Tackling Cybersickness Attacks with Explainable AI 17 Mar 2025 · 0 repositories · arXiv:2503.13419
-
Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction 12 Mar 2025 · 1 repository · arXiv:2503.09040
-
OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels 27 Feb 2025 · 1 repository · arXiv:2502.20087Syntology ran 0 of 3 samples · 3 unverified
-
GHOST 2.0: generative high-fidelity one shot transfer of heads 25 Feb 2025 · 0 repositories · arXiv:2502.18417
-
Analysis and Prediction of Coverage and Channel Rank for UAV Networks in Rural Scenarios with Foliage 14 Feb 2025 · 0 repositories · arXiv:2502.10324
-
Hybrid Answer Set Programming: Foundations and Applications 13 Feb 2025 · 0 repositories · arXiv:2502.09235
-
SASVi - Segment Any Surgical Video 12 Feb 2025 · 1 repository · arXiv:2502.09653
Tasks archive 2025-07-28
20 shown of 409 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