Trending

Show HN: Controlling 3D models with voice and hand gestures

Vision Language Models Are Biased

RenderFormer: Neural Rendering of Triangle Meshes with Global Illumination

Making maps with noise functions (2022)

YOLO-World: Real-Time Open-Vocabulary Object Detection

Colour and Shape: Using Computer Vision to Explore the Science Museum (2020)

Investigating AI Manipulation in Viral Chinese Paraglider Video

Turn a Tesla into a mapping vehicle with Mapillary

Show HN: Free mammogram analysis tool combining deep learning and vision LLM

Futuristic pixel-raising display lets you feel what’s onscreen

Meta released Map-anything-v1: A universal transformer model for metric 3D reconstruction

Apple introduces SHARP, a model that generates a photorealistic 3D Gaussian representation from a single image in seconds.

Microsoft's TRELLIS 2-4B, An Open-Source Image-to-3D Model

Bodycam footage reveals moment innocent man is arrested after AI misidentifies him

Self-driving Waymo vehicles repeatedly passed stopped school buses, officials say

Exploring a more direct way to edit AI images after getting frustrated myself

Soft robots can now see with a self-focusing squishy eye

Meta AI translates peoples words into different languages and edits their mouth movements to match

Microsoft

Save item

TRELLIS.2-4B

Task: image-to-3d

Apple

Save item

Sharp

Task: image-to-3d

Quark Vision Group

Save item

Live-Avatar

Tencent

Save item

HunyuanOCR

Task: image-text-to-text

City

Save item

FLUX.2-dev-gguf

Task: image-to-image

Phr00t

Save item

Qwen-Image-Edit-Rapid-AIO

Task: text-to-image

Black Forest Labs

Save item

FLUX.1-dev

Task: text-to-image

AI at Meta

Save item

sam-3d-body-dinov3

wuli-DX

Save item

Qwen-Image-Edit-2509-Fusion

Task: image-to-image

deepinsight

Save item

insightface

State-of-the-art 2D and 3D Face Analysis Project

Project-MONAI

Save item

MONAI

AI Toolkit for Healthcare Imaging

upscayl

Save item

upscayl

🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

microsoft

Save item

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

sympy

Save item

sympy

A computer algebra system written in pure Python

IntelRealSense

Save item

librealsense

Intel® RealSense™ SDK

facebookresearch

Save item

habitat-sim

A flexible, high-performance 3D simulator for Embodied AI research.

huggingface

Save item

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

open-mmlab

Save item

mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.