Computer Vision › Core AI ›

Efficient Computing

179 directly classified papers

Papers per year

Papers

Motion-adaptive Transformer for Event-based Image Deblurring AAAI 2025

AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints AAAI 2025

ActiveGAMER: Active GAussian Mapping through Efficient Rendering CVPR 2025

LSNet: See Large, Focus Small CVPR 2025

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba ICCV 2025

Erasing Undesirable Influence in Diffusion Models CVPR 2025

Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025

Column-Oriented Datalog on the GPU AAAI 2025

Building Vision Models upon Heat Conduction CVPR 2025

EDM: Efficient Deep Feature Matching ICCV 2025

PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction ICCV 2025

TurboVSR: Fantastic Video Upscalers and Where to Find Them ICCV 2025

SpiralMLP: A Lightweight Vision MLP Architecture WACV 2025

RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone WACV 2025

U-MixFormer: UNet-Like Transformer with Mix-Attention for Efficient Semantic Segmentation WACV 2025

LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones WACV 2025

RefVSR++: Exploiting Reference Inputs for Reference-Based Video Super-Resolution WACV 2025

Stable Autofocus with Focal Consistency Loss WACV 2025

V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations WACV 2025

Self-Aligning Depth-Regularized Radiance Fields for Asynchronous RGB-D Sequences WACV 2025

Unifying Low-Resolution and High-Resolution Alignment by Event Cameras for Space-Time Video Super-Resolution WACV 2025

MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge ICCV 2025

All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising CVPR 2025

Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales CVPR 2025

ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition AAAI 2025