Computer Vision

I built a free alternative to Screen Studio and Focusee

Estimating Individual Tree Height and Species from UAV Imagery

Revealing Multi-View Hallucination in Large Vision-Language Models

High-Fidelity Face Content Recovery via Tamper-Resilient Versatile Watermarking

Language-Guided Structure-Aware Network for Camouflaged Object Detection

SEGAR: Selective Enhancement for Generative Augmented Reality

LensWalk: Agentic Video Understanding by Planning How You See in Videos

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

DIDLM: A SLAM Dataset for Difficult Scenarios Featuring Infrared, Depth Cameras, LIDAR, 4D Radar, and Others under Adverse Weather, Low Light Conditions, and Rough Roads

RestoreVAR: Visual Autoregressive Generation for All-in-One Image Restoration

Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting

Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition

Skin Health at the Edge: Deploying Custom Vision Transformers (ViT) on iOS with CoreML

Intel and LG Display may have beaten Apple and Qualcomm with the best laptop battery life ever

My Study Notes on Convolutional Neural Networks (CNN)

We Just Launched Virtual Try-On in Our API — Here's How It Actually Works (With Real Results)

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal

Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing

UAV-DETR: DETR for Anti-Drone Target Detection

UniQueR: Unified Query-based Feedforward 3D Reconstruction

YOLOv10 with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection and trustworthy multimodal AI in computer vision perception

PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion

MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classification

Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench

Pedestrian Crossing Intention Prediction Using Multimodal Fusion Network

LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction

Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation

Arm is releasing the first in-house chip in its 35-year history

Real-Time Block Computing: Track Physical Objects & Bounce Digital Elements Off Them

Tinyvision:-Building Ultra-Lightweight Models for Image Tasks(Part-1)

Ugreen Reveals Its New Generation Maxidok Thunderbolt 5 Docks

Deploying CVAT on AWS for Image and Video Annotation

Computer Vision Toolkit

Teaching Machines to See (Part 1): Why Vision Is Hard

A 10-Year Age Swing from Lighting Alone — What Facial Algorithms Are Really Measuring

LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment

Toward High-Fidelity Visual Reconstruction: From EEG-Based Conditioned Generation to Joint-Modal Guided Rebuilding

RAM: Recover Any 3D Human Motion in-the-Wild

From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering

Adaptive Relative Pose Estimation Framework with Dual Noise Tuning for Safe Approaching Maneuvers

3D-Consistent Multi-View Editing by Correspondence Guidance

Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors

CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

Is Apple's New MacBook Pro Right For You?

Yes, 8GB of RAM really is enough for a MacBook in 2026 - here's why

Forget Blender Skills: This AI Generates Complete 3D Objects for You

RF-DETR vs YOLO vs Cloud API: Which Should You Actually Use in 2026?

Deploying a Image Recognition Service to AWS Lambda