Hacker News with Generative AI: Computer Vision

Hand Tracking for Mouse Input (2023) (chernando.com)
The other day I saw the launch of Apple Vision Pro, the whole thing was very interesting, but one thing that caught my attention was the finger input. It seems very intuitive, by using the finger pinching as sort of like a cursor or mouse input. I figured I want to try it out, so I took it upon myself to create it.
Hand Tracking, User Interface, Software, Computer Vision
217 points by wonger_ 2 days ago | 49 comments
GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation (nirvanalan.github.io)
GaussianAnything generates high-quality and editable surfel Gaussians through a cascaded 3D diffusion pipeline, given single-view images or texts as the conditions.
Generative AI, 3D Modeling, Machine Learning, Computer Vision
82 points by lnyan 3 days ago | 9 comments
LLaVA-O1: Let Vision Language Models Reason Step-by-Step (arxiv.org)
Large language models have demonstrated substantial advancements in reasoning capabilities, particularly through inference-time scaling, as illustrated by models such as OpenAI's o1. However, current Vision-Language Models (VLMs) often struggle to perform systematic and structured reasoning, especially when handling complex visual question-answering tasks.
Computer Vision, Reasoning, Artificial Intelligence
176 points by lnyan 3 days ago | 32 comments
All-in-one embedding model for interleaved text, images, and screenshots (voyageai.com)
TL;DR — We are excited to announce voyage-multimodal-3, a new state-of-the-art for multimodal embeddings and a big step forward towards seamless RAG and semantic search for documents rich with both visuals and text. Unlike existing multimodal embedding models, voyage-multimodal-3 is capable of vectorizing interleaved texts + images and capturing key visual features from screenshots of PDFs, slides, tables, figures, and more, thereby eliminating the need for complex document parsing.
Multimodal Embeddings, Artificial Intelligence, Computer Vision
261 points by fzliu 4 days ago | 31 comments
Show HN: ColiVara – State of the Art RAG API with Vision Models (github.com/tjmlabs)
ColiVara = COntextualized Late Interaction Vision Augmented Retrieval API
Computer Vision, APIs, Open Source, AI, Machine Learning
10 points by jonathan-adly 5 days ago | 0 comments
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization (rccchoudhury.github.io)
We present Run-Length Tokenization (RLT), a simple and efficient approach to speed up video transformers by removing redundant tokens from the input.
Computer Vision, Machine Learning, Video Processing, Deep Learning, Transformers
74 points by jasondavies 5 days ago | 16 comments
Omnivision-968M: Vision Language Model with 9x Tokens Reduction for Edge Devices (nexa.ai)
Computer Vision, Edge Computing, AI Models, Tokenization
69 points by BUFU 6 days ago | 10 comments
Image-Text Curation for 1B+ Data: Faster, Better, Smaller Clip Models (datologyai.com)
Computer Vision, Data Science, Generative AI, Language Models
12 points by hurrycane 7 days ago | 0 comments
Benchmarking Vision, Language, and Action Models on Robotic Learning Tasks (multinet.ai)
Vision-language-action (VLA) models represent a promising direction for developing general-purpose robotic systems, demonstrating the ability to combine visual understanding, language comprehension, and action generation.
Robotics, Artificial Intelligence, Computer Vision, Machine Learning
11 points by hsikka 8 days ago | 0 comments
Watermark Anything (github.com/facebookresearch)
Implementation and pretrained models for the paper Watermark Anything. Our approach allows for embedding (possibly multiple) localized watermarks into images.
Computer Vision, Image Processing, Artificial Intelligence, Open Source, Facebook Research
314 points by zerojames 9 days ago | 108 comments
FLUX1.1 a Prompt Like "IMG_1018.CR2" (twitter.com)
Image Processing, Computer Vision, Machine Learning, Programming
18 points by amrrs 10 days ago | 2 comments
Drone Relative Positioning (matthew-bird.com)
My plan for this project was to determine the relative positioning and orientation of two or more objects with cameras using minimal usage of external libraries. I was inspired to do this by drone shows in HK.
Drone Technology, Computer Vision
59 points by mooreds 12 days ago | 17 comments
SVDQuant: 4-Bit Quantization Powers 12B Flux on a 16GB 4090 GPU with 3x Speedup (hanlab.mit.edu)
A new post-training training quantization paradigm for diffusion models, which quantize both the weights and activations of FLUX.1 to 4 bits, achieving 3.5× memory and 8.7× latency reduction on a 16GB laptop 4090 GPU.
Machine Learning, Deep Learning, Computer Vision, Hardware, Quantization
179 points by lmxyy 12 days ago | 65 comments
Neural Optical Flow for PIV in Fluids (synthical.com)
Neural Networks, Fluid Dynamics, Computer Vision
15 points by mixeden 12 days ago | 8 comments
Five Learnings from 15 Years in Perception (tangramvision.com)
In the fall of 2008, I was working on my third startup, ReTel Technologies. Our goal was to analyze shopper behavior in grocery stores, and use that data to help stores and brands improve the customer experience and store profitability. But we had a challenge: how do you anonymously track hundreds of shoppers per day in a store? We thought we had the answer: active RFID tags on every shopping cart.
Computer Vision, Retail, Startups, Machine Learning
67 points by reteltech 14 days ago | 26 comments
Peng quadrotor autonomy framework visualized in the browser (rerun.io)
Rerun is not yet supported on mobile browsers.
Robotics, Computer Vision, Web Development, Visualization
32 points by Tycho87 14 days ago | 2 comments
Harnessing Vision for Computation (2008) [pdf] (changizi.com)
Computer Vision, Computational Neuroscience, Artificial Intelligence
7 points by robinhouston 14 days ago | 0 comments
Ollama 0.4 is released with support for Meta's Llama 3.2 Vision models locally (ollama.com)
Llama 3.2 Vision is now available to run in Ollama, in both 11B and 90B sizes.
New Releases, Generative AI, Computer Vision, Open Source
182 points by BUFU 14 days ago | 25 comments
Iterative α-(de)blending and Stochastic Interpolants (nicktasios.nl)
In this post I'm looking into a paper the authors of which promise to make diffusion models simple to understand and implement, called Iterative α-(de)blending1, and find out that this promise is only partially fulfilled, at least personally. I reproduce the algorithm from the paper and apply it to the generation of MNIST digits, like I did in the previous series of posts, and find out that something is missing.
Generative AI, Machine Learning, Computer Vision, Research
24 points by lapnect 15 days ago | 1 comments
GenXD: Generating Any 3D and 4D Scenes (arxiv.org)
Recent developments in 2D visual generation have been remarkably successful. However, 3D and 4D generation remain challenging in real-world applications due to the lack of large-scale 4D data and effective model design.
3D Modeling, 4D Modeling, Computer Vision, Artificial Intelligence, Generative Models
9 points by sandwichsphinx 15 days ago | 0 comments
TextLap: Customizing Language Models for Text-to-Layout Planning (arxiv.org)
Automatic generation of graphical layouts is crucial for many real-world applications, including designing posters, flyers, advertisements, and graphical user interfaces.
Generative AI, Computer Vision, Design, Machine Learning
8 points by PaulHoule 16 days ago | 0 comments
Self-Occluded Avatar Recovery from a Single Video in the Wild (soar-avatar.github.io)
A Unified Framework Self-occlusion is common when capturing people in the wild, where the performers do not follow predefined motion scripts. This challenges existing monocular human reconstruction systems that assume full body visibility. We introduce Self-Occluded Avatar Recovery (SOAR), a method for complete human reconstruction from partial observations where parts of the body are entirely unobserved. SOAR leverages structural normal prior and generative diffusion prior to address such an ill-posed reconstruction problem.
Computer Vision, Generative AI, Artificial Intelligence, 3D Reconstruction
8 points by Hard_Space 16 days ago | 0 comments
ThunderKittens: Simple, fast, and adorable AI kernels (hazyresearch.stanford.edu)
Fiveish months ago, we put out our posts on ThunderKittens and GPUs, and were pleasantly surprised by their warm reception on The Platform Formerly Known as Twitter.
AI, Generative AI, Computer Vision, Machine Learning
87 points by lnyan 22 days ago | 18 comments
A return to hand-written notes by learning to read and write (research.google)
We present a model to convert photos of handwriting into a digital format that reproduces component pen strokes, without the need for specialized equipment.
Handwriting, AI, Computer Vision, Digitalization
595 points by mfiguiere 23 days ago | 181 comments
RebrickNet – Lego Part Detector (rebrickable.com)
RebrickNet learns by looking at images of LEGO parts and discovering the features that make each part unique.
Machine Learning, LEGO, Computer Vision
107 points by wonger_ 25 days ago | 40 comments
Leopard: A Vision Language Model for Text-Rich Multi-Image Tasks (arxiv.org)
Text-rich images, where text serves as the central visual element guiding the overall understanding, are prevalent in real-world applications, such as presentation slides, scanned documents, and webpage snapshots.
Computer Vision, Artificial Intelligence, Image Processing
6 points by PaulHoule 26 days ago | 0 comments
OmniParser for Pure Vision Based GUI Agent (microsoft.github.io)
The recent success of large vision language models shows great potential in driving the agent system operating on user interfaces.
User Interfaces, Artificial Intelligence, Computer Vision
145 points by fzliu 27 days ago | 34 comments
Claude Computer Use – Is Vision the Ultimate API? (thariq.io)
I’ve spent the last 2 days basically non-stop hacking with Anthropic’s Computer Use API.
Computer Vision, APIs, Artificial Intelligence
113 points by trq_ 28 days ago | 90 comments
Seeing faces in things: A model and dataset for pareidolia (mhamilton.net)
The human visual system is well-tuned to detect faces of all shapes and sizes. While this brings obvious survival advantages, such as a better chance of spotting unknown predators in the bush, it also leads to spurious face detections. "Face pareidolia" describes the perception of face-like structure among otherwise random stimuli: seeing faces in coffee stains or clouds in the sky. In this paper, we study face pareidolia from a computer vision perspective.
Computer Vision, Psychology, Artificial Intelligence, Datasets
61 points by sebg 30 days ago | 9 comments
Transformers Utilization in Chart Understanding: A Review of Advances and Future (arxiv.org)
In recent years, interest in vision-language tasks has grown, especially those involving chart interactions.
Transformers, Machine Learning, Computer Vision, Data Visualization
39 points by sandwichsphinx 30 days ago | 2 comments