sangminwoo/Depth_from_Focus

Stars
56
Rank 527,638 (Top 11 %)
Language
Python
License
MIT License
Created almost 5 years ago
Updated over 3 years ago

sangminwoo/Depth_from_Focus

sangminwoo

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Conventional Depth from Focus(DfF) estimation with slight focus variations in image sequences

awesome-vision-and-language

A curated list of awesome vision and language resources (still under construction... stay tuned!)

Explore-And-Match

Official pytorch implementation of "Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos"

RecycleNet

Attentional Learning of Trash Classification

ActionMAE

[AAAI 2023] Official pytorch implementation of "Towards Good Practices for Missing Modality Robust Action Recognition"

Temporal-Span-Proposal-Network-VidVRD

What and When to look?: Temporal Span Proposal Network for Video Relation Detection

Local-to-Global-Interaction-Networks-SGG

[TNNLS 2022] Official pytorch implementation of "Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions"

Jupyter Notebook

DMP

Official pytorch implementation of "Diffusion Model Patching via Mixture-of-Prompts"

RITUAL

Official pytorch implementation of "RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in LVLMs"

AvisC

Official pytorch implementation of "Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models"

explore-and-match

Explore-and-Match: A New Paradigm for Temporal Video Grounding with Natural Language

Structure-from-Motion

Structure from Motion(SfM) with slight different view of images

evo_ai

Evolutionary Algorithms (knapsack problem, traveling salesman problem, 4bit deceptive problem, neural network architecture optimization)

SVOL

[WACV 2024] Official pytorch implementation of "SVOL: Sketch-based Video Object Localization"

Attention-in-CNN

Attention Module in CNN (ResNet + CIFAR100)

Cost-Out-Multitask-Learning

[Electronics] Revisiting Dropout: Escaping Pressure for Training Neural Networks with Multiple Costs