👁️ Computer vision - plooh · Scour

SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness 🎨Neural Rendering

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers 📱Edge AI

BEVal: A Cross-dataset Evaluation Study of BEV Segmentation Models for Autonomous Driving 📊SLAM Datasets

GenMatter: Perceiving Physical Objects with Generative Matter Models 🎨Neural Rendering

FruitProM-V2: Robust Probabilistic Maturity Estimation and Detection of Fruits and Vegetables 👁️‍🗨️Multimodal Sensing

Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures 🎨Neural Rendering

Learning from Noisy Prompts: Saliency-Guided Prompt Distillation for Robust Segmentation with SAM 🎨Neural Rendering

Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models 🎨Neural Rendering

Exploring Audio Hallucination in Egocentric Video Understanding 👁️‍🗨️Multimodal Sensing

GateMOT: Q-Gated Attention for Dense Object Tracking ⚡Event Cameras

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation 📱Edge AI

From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation ⚡Event Cameras

2D Pre-Training for 3D Pose Estimation 📊SLAM Datasets

Geometric Analysis of Self-Supervised Vision Representations for Semantic Image Retrieval 📊SLAM Datasets

HAC: Parameter-Efficient Hyperbolic Adaptation of CLIP for Zero-Shot VQA 📊SLAM Datasets

H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers 👁️‍🗨️Multimodal Sensing

ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning 📊SLAM Datasets

PEPS: Positional Encoding Projected Sampling -- Extended 🎨Neural Rendering

Learning to Decipher from Pixels -- A Case Study of Copiale 📱Edge AI

From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models 📱Edge AI

Sign up or log in to see more results

Log in to enable infinite scrolling