MobileAI22
* *Mobile AI
* Efficient Hybrid Model for Low-light Image Enhancement in Mobile Devices, An
* PhoneDepth: A Dataset for Monocular Depth Estimation on Mobile Devices
* RenderSR: A Lightweight Super-Resolution Model for Mobile Gaming Upscaling
* SMM-Conv: Scalar Matrix Multiplication with Zero Packing for Accelerated Convolution
* Update Compression for Deep Neural Networks on the Edge
MobileAI23
* *Mobile AI
* DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow
* High-efficiency Device-Cloud Collaborative Transformer Model
* MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications
* QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms
* Real-time Segmenting Human Portrait at Anywhere
* VideoMatt: A Simple Baseline for Accessible Real-Time Video Matting
7 for MobileAI23
MobileAI24
* *Mobile AI
* CoDISP: Exploring Compressed Domain Camera ISP with RGB-guided Encoder
* Efficient Skeleton-Based Action Recognition for Real-Time Embedded Systems
* End-to-End Neural Network Compression via l1/l2 Regularized Latency Surrogates
* Scaling Graph Convolutions for Mobile Vision
MobileAI25
* *Mobile AI
* ActNAS: Generating Efficient YOLO Models Using Activation NAS
* CDVS: Compressed Domain On Device Memory Efficient 8K Video SlowMo
* Compressed Domain Multiframe Processing
* Cycle Training with Semi-Supervised Domain Adaptation: Bridging Accuracy and Efficiency for Real-Time Mobile Scene Detection
* Flar-SVD: Fast and Latency-Aware Singular Value Decomposition for Model Compression
* Learned Lightweight Smartphone ISP with Unpaired Data
* Learned Smartphone ISP on Mobile GPUs, Mobile AI 2025 Challenge: Report
* PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers
* Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2025 Challenge: Report
* RepFC: Universal Structural Reparametrization Block for High Performance, Lightweight Deep Neural Networks
* RGB Photo Enhancement on Mobile GPUs, Mobile Ai 2025 Challenge: Report
* Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
13 for MobileAI25