Skip to content

PaperCodex

Subscribe

Efficient Deep Learning

AANet: Real-Time Stereo Matching Without 3D Convolutions for Autonomous Systems and Embedded Vision

AANet: Real-Time Stereo Matching Without 3D Convolutions for Autonomous Systems and Embedded Vision 548

Stereo matching—the task of estimating depth from a pair of rectified images—is foundational in applications like autonomous driving, robotics, and…

01/13/2026Depth Estimation, Efficient Deep Learning, Stereo Matching
MambaOut: High-Accuracy Vision Models Without the Mamba Overhead

MambaOut: High-Accuracy Vision Models Without the Mamba Overhead 2609

The vision community has recently seen a surge in adopting sequence modeling architectures—especially Mamba—for image tasks. Inspired by its linear…

12/26/2025Efficient Deep Learning, Image Classification, Vision Backbone
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex