Hacker News with Generative AI: Computer Vision

Self-Supervised Learning from Images with JEPA (2023) (arxiv.org)
This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations.
Self-Supervised Learning, Computer Vision, Image Recognition, Artificial Intelligence, Deep Learning
40 points by Brysonbw 4 days ago | 10 comments
How DeepSeek Rewrote the Transformer [video] (youtube.com)
Transformers, Deep Learning, Computer Vision, Artificial Intelligence, Video
5 points by chetangole 5 days ago | 0 comments
Estimating Camera Motion from a Single Motion-Blurred Image (jerredchen.github.io)
Given a single motion-blurred image, we exploit the motion blur cues to predict the camera velocity at that instant without performing any deblurring.
Computer Vision, Image Processing, Motion Estimation
69 points by smusamashah 5 days ago | 19 comments
VGGT: Visual Geometry Grounded Transformer (github.com/facebookresearch)
Computer Vision, Transformers, Artificial Intelligence, Deep Learning, Facebook Research
190 points by xnx 8 days ago | 42 comments
Open source AI agent helper to let it SEE what its doing (github.com/monteslu)
An MCP server that enables LLMs to "see" what's happening in browser-based games and applications through vectorized canvas visualization and debug information.
Open source, AI agents, Computer Vision, Gaming
9 points by monteslu 8 days ago | 2 comments
The Original 2012 AlexNet Is Open Source Now (github.com/computerhistory)
This package contains the original 2012 AlexNet code.
Computer Vision, Deep Learning, Open Source, Machine Learning, History
3 points by kwiktrip 8 days ago | 0 comments
Can Large Vision Language Models Read Maps Like a Human? (arxiv.org)
Computer Vision, Artificial Intelligence, Maps
9 points by thinkingemote 9 days ago | 1 comments
Can Large Vision Language Models Read Maps Like a Human? (arxiv.org)
In this paper, we introduce MapBench-the first dataset specifically designed for human-readable, pixel-based map-based outdoor navigation, curated from complex path finding scenarios.
Generative AI, Computer Vision, Maps, Navigation, Artificial Intelligence
3 points by eamag 10 days ago | 0 comments
Intel RealSense Stereo Depth Cameras (intelrealsense.com)
Stereo Depth cameras, Lidar cameras, Coded light and Tracking cameras from Intel RealSense
Computer Vision, Hardware, Intel, 3D Scanning
96 points by 1sembiyan 10 days ago | 65 comments
Map Features in OpenStreetMap with Computer Vision (mozilla.ai)
Mozilla.ai developed and released the OpenStreetMap AI Helper Blueprint. If you love maps and are interested in training your own computer vision model, you’ll enjoy diving into this Blueprint.
Computer Vision, Machine Learning, Mapping, Open Source, Mozilla
306 points by Brysonbw 11 days ago | 75 comments
Show HN: Torch Lens Maker – Differentiable Geometric Optics in PyTorch (victorpoughon.github.io)
Welcome to Torch Lens Maker, an open-source Python library for differentiable geometric optics based on PyTorch. Currently a very experimental project, the goal is to be able to design complex real-world optical systems (lenses, mirrors, etc.) using modern computer code and state-of-the art numerical optimization.
Open Source, Computer Vision, Python, Machine Learning, Optics
179 points by fouronnes3 12 days ago | 45 comments
Nvidia GTC 2025 – Built for Reasoning, Vera Rubin, Kyber, Jensen Math, Feynman (semianalysis.com)
AI model progress has accelerated tremendously, and in the last six months, models have improved more than in the previous six months. This trend will continue because three scaling laws are stacked together and working in tandem: pre-training scaling, post-training scaling, and inference time scaling.
Nvidia, Generative AI, Computer Vision, Machine Learning, Artificial Intelligence
10 points by nabla9 12 days ago | 0 comments
SmolDocling: An ultra-compact VLM for end-to-end multi-modal document conversion (arxiv.org)
We introduce SmolDocling, an ultra-compact vision-language model targeting end-to-end document conversion.
Vision-Language Models, Document Conversion, Machine Learning, Computer Vision
66 points by prats226 12 days ago | 12 comments
Feature maps from CNNs have a weird similarity to ancient Egyptian hieroglyphs (twitter.com)
Something went wrong, but don’t fret — let’s give it another shot.
Artificial Intelligence, Computer Vision, Machine Learning, History
4 points by capela 14 days ago | 0 comments
Tesla Autopilot Car Drove Through a Giant Photo of a Road (petapixel.com)
Famous YouTube creator and former NASA engineer Mark Rober, who provides his 65 million subscribers with scientific entertainment videos, put Tesla’s vision-based safety features up against a LiDAR system, and the results, although arguably flawed, highlight the limitations of vision-based autonomous vehicle systems.
Tesla, Autonomous Vehicles, Artificial Intelligence, Computer Vision
9 points by dxs 15 days ago | 2 comments
Arbitrary-Scale Super-Resolution with Neural Heat Fields (therasr.github.io)
Thera is the first arbitrary-scale super-resolution method with a built-in physical observation model.
Super-Resolution, Image Processing, Computer Vision, Artificial Intelligence, Neural Networks
151 points by 0x12A 18 days ago | 56 comments
Gemma3 – The current strongest model that fits on a single GPU (ollama.com)
Gemma is a lightweight, family of models from Google built on Gemini technology. The Gemma 3 models are multimodal—processing text and images—and feature a 128K context window with support for over 140 languages. Available in 1B, 4B, 12B, and 27B parameter sizes, they excel in tasks like question answering, summarization, and reasoning, while their compact design allows deployment on resource-limited devices.
Generative AI, AI Models, Multimodal AI, Computer Vision
252 points by brylie 21 days ago | 138 comments
Show HN: 6DoF Object detection and tracking in web browser – WebAR.rocks.train (github.com/WebAR-rocks)
Web Development, Computer Vision, Augmented Reality, Machine Learning, JavaScript
12 points by xavierwebgl 22 days ago | 0 comments
Gaussian Splats with OpenScene (ashwanirathee.com)
Exploring 3D Gaussian Splatting for Novel View Synthesis
3D Graphics, Computer Vision, OpenScene, Gaussian Splats
3 points by ashwani-rathee 23 days ago | 0 comments
Smaller but Better: Unifying Layout Generation with Smaller LLMs (arxiv.org)
We propose LGGPT, an LLM-based model tailored for unified layout generation.
Artificial Intelligence, Computer Vision, Generative AI, Research
24 points by PaulHoule 25 days ago | 3 comments
Nexar Dashcam Crash Prediction Challenge (kaggle.com)
Computer Vision, Machine Learning, Data Science, Competitions
10 points by dmoura 26 days ago | 4 comments
AMD YOLO (geohot.github.io)
AMD is sending us the two MI300X boxes we asked for. They are in the mail.
AMD, Hardware, AI, Computer Vision
120 points by trulyrandom 26 days ago | 82 comments
Nvidia OCR (nvidia.com)
Cutting-edge vision-language model exceling in retrieving text and metadata from images.
Computer Vision, Artificial Intelligence, Nvidia
9 points by mightysmaug 26 days ago | 0 comments
InstantStyle: Free Lunch Towards Style-Preserving in Text-to-Image Generation (github.com/instantX-research)
InstantStyle is a general framework that employs two straightforward yet potent techniques for achieving an effective disentanglement of style and content from reference images.
Generative AI, Computer Vision, Machine Learning, Image Generation, Deep Learning
49 points by klaussilveira 26 days ago | 11 comments
GEN3C: 3D-Informed World-Consistent Video (huggingface.co)
We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency.
Generative AI, Video, 3D, Computer Vision
3 points by jacobedawson 27 days ago | 1 comments
16-Bit to 1-Bit: Visual KV Cache Quantization for Efficient Multimodal LLMs (arxiv.org)
Multimodal Large Language Models (MLLMs) have achieved remarkable success across various applications, yet their computational overhead during deployment remains a critical challenge.
Computer Vision, Artificial Intelligence, Optimization, Quantization
87 points by PaulHoule 28 days ago | 1 comments
Show HN: Vidformer – Drop-In Acceleration for Cv2 Video Annotation Scripts (github.com/ixlab)
A research project providing infrastructure for video-native interfaces and accelerating computer vision visualization. Developed by the OSU Interactive Data Systems Lab.
Computer Vision, Video Annotation, Research Projects, Open Source
25 points by dominikwin 29 days ago | 11 comments
SpeciesNet: AI models to classify species from motion-triggered widlife cameras (github.com/google)
Effective wildlife monitoring relies heavily on motion-triggered wildlife cameras, or “camera traps”, which generate vast quantities of image data. Manual processing of these images is a significant bottleneck. AI can accelerate that processing, helping conservation practitioners spend more time on conservation, and less time reviewing images.
Artificial Intelligence, Wildlife Conservation, Computer Vision, Conservation Technology
7 points by rguiscard 29 days ago | 1 comments
Putting Andrew Ng's OCR models to the test (runpulse.com)
Today, Andrew Ng, one of the legends of the AI world, released a new document extraction service that went viral on X.
Artificial Intelligence, Computer Vision, OCR, Andrew Ng
124 points by ritvikpandey21 33 days ago | 61 comments
Replace OCR with Vision Language Models (github.com/vlm-run)
Computer Vision, Machine Learning
292 points by EarlyOom 35 days ago | 125 comments