Computer Vision

arXiv:2605.08169v1 Announce Type: cross Abstract: Automated culprit identification in surveillance systems is a critical task that requires high accuracy along

arXiv:2605.08222v1 Announce Type: cross Abstract: Handwritten archival tables contain rich historical information, yet transforming them into structured represe

arXiv:2605.08325v1 Announce Type: cross Abstract: Many vision datasets now provide segmentation masks in addition to annotated images to support a wide range of

arXiv:2605.08389v1 Announce Type: cross Abstract: Zero-shot composed image retrieval (ZS-CIR) retrieves a target image from a reference image and a text modific

arXiv:2605.08651v1 Announce Type: cross Abstract: Video anomaly detection (VAD) systems often prioritize accuracy while overlooking privacy concerns, limiting t

arXiv:2605.08727v1 Announce Type: cross Abstract: Learned image compression (LIC) integrates deep neural networks (DNNs) to map high-dimensional images into com

arXiv:2605.08808v1 Announce Type: cross Abstract: Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense ca

arXiv:2605.08902v1 Announce Type: cross Abstract: In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a cruci

arXiv:2605.08971v1 Announce Type: cross Abstract: Computer-Aided Design is ubiquitous in todays world, as almost every manufactured object begins as a digital m

arXiv:2605.09002v1 Announce Type: cross Abstract: In this retrospective multi-institutional study, a quantitative phenotyping framework, CT-IDP (CT Image-Derive

arXiv:2605.09090v1 Announce Type: cross Abstract: Visual Grounding benchmarks assume that the object described by a referring expression is always present in th

arXiv:2605.09233v1 Announce Type: cross Abstract: Recent advances in visual generative models have enabled high-fidelity image editing guided by human instructi

arXiv:2605.09339v1 Announce Type: cross Abstract: Human color categories are not uniformly distributed in perceptual space, yet most computational color models

arXiv:2605.09538v1 Announce Type: cross Abstract: While existing methods for reconstructing hand-object interactions have made impressive progress, they either

arXiv:2605.09667v1 Announce Type: cross Abstract: We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathem

arXiv:2605.09802v1 Announce Type: cross Abstract: Vision-language models (VLMs) enable text-guided object detection but degrade severely under cross-view scenar

arXiv:2605.09856v1 Announce Type: cross Abstract: Although recent studies have made remarkable progress in human mesh recovery, they still exhibit limited robus

arXiv:2605.09874v1 Announce Type: cross Abstract: Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems,

arXiv:2605.09956v1 Announce Type: cross Abstract: High-quality, real-time talking head synthesis remains a fundamental challenge in computer vision. Existing re

arXiv:2605.09984v1 Announce Type: cross Abstract: Recent 4D generation methods complete scene-level missing information using generative models and reconstruct

arXiv:2605.10100v1 Announce Type: cross Abstract: We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning ent

arXiv:2605.10142v1 Announce Type: cross Abstract: Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear

arXiv:2605.10185v1 Announce Type: cross Abstract: Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured i

arXiv:2605.10661v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear ho

arXiv:2605.10732v1 Announce Type: cross Abstract: Automated transit payment analysis is vital for scalable fare auditing and passenger analytics, yet practice s

arXiv:2605.10780v1 Announce Type: cross Abstract: Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved st

arXiv:2605.10833v1 Announce Type: cross Abstract: Industrial anomaly detection is critical for manufacturing quality control, yet existing datasets mainly focus

arXiv:2402.02286v4 Announce Type: replace-cross Abstract: U-shaped architectures have long dominated the field of medical image segmentation, while Transformers

arXiv:2505.23617v3 Announce Type: replace-cross Abstract: Effective video tokenization is critical for scaling transformer models for long videos. Current appro

arXiv:2603.14694v2 Announce Type: replace-cross Abstract: Rapid structural damage assessment from remote sensing imagery is essential for timely disaster respon

One camera feed. Real Tesla footage. A full 3D world. Continue reading on Medium »

A step‑by‑step guide to train, containerize, and serve a custom YOLOv8 model with low‑latency FastAPI endpoints, Docker, and GitHub Actions

Validating Passport Photos for 3 of the Strictest Government Portals (India, China,...

arXiv:2605.06714v1 Announce Type: cross Abstract: Edge deep learning, a paradigm change reconciling edge computing and deep learning, facilitates real-time deci

arXiv:2605.06927v1 Announce Type: cross Abstract: Object detection on heterogeneous edge devices must satisfy strict energy, latency, and memory constraints whi

arXiv:2605.07151v1 Announce Type: cross Abstract: Urban spatial evolution is manifested not only through horizontal expansion but also through vertical structur

arXiv:2605.07317v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-preci

arXiv:2605.07604v1 Announce Type: cross Abstract: 3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions,

arXiv:2605.07786v1 Announce Type: cross Abstract: As generative models achieve unprecedented visual quality, the gold standard for image evaluation remains trad

arXiv:2605.07897v1 Announce Type: cross Abstract: Online streaming video understanding requires models to process continuous visual inputs and respond to user q

arXiv:2605.08043v1 Announce Type: cross Abstract: While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual i

arXiv:2605.08073v1 Announce Type: cross Abstract: Recent event-based image reconstruction methods predominantly rely on Convolutional Neural Networks (CNNs) and

arXiv:2509.12047v2 Announce Type: replace-cross Abstract: Animal behavior analysis plays a crucial role in understanding animal welfare, health status, and prod

arXiv:2601.15356v5 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has empowered Multimodal Large Language Models (MLLMs) to achieve superior

arXiv:2603.12647v2 Announce Type: replace-cross Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene re

arXiv:2603.21824v2 Announce Type: replace-cross Abstract: Steel surface defect analysis is critical for industrial quality control, yet existing benchmarks rely

Research papers on pose estimation show impressive accuracy numbers. Production apps on consumer...

This project speaks for itself. It covers three crucial steps in one go: motion tracking, skeleton reconstruction, and 3D animation. What… Continue reading on M