Hacker News with Generative AI: Computer Vision

Three things everyone should know about Vision Transformers (arxiv.org)
After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and video analysis.
Computer Vision, Transformers, Artificial Intelligence, Deep Learning
67 points by reqo 2 days ago | 16 comments
π0.5: A VLA with open-world generalization (pi.website)
Robots have come a long way over the past few years—they can perform impressive acrobatic feats, dance on stage, follow language commands and, in some of our own results, perform complex tasks like folding laundry or cleaning off a table. But the biggest challenge in robotics is not in performing feats of agility or dexterity, but generalization: the ability to figure out how to correctly perform even a simple task in a new setting or with new objects.
Robotics, Artificial Intelligence, Machine Learning, Computer Vision
175 points by lachyg 3 days ago | 44 comments
Gemma 3 QAT Models: Bringing AI to Consumer GPUs (googleblog.com)
Last month, we launched Gemma 3, our latest generation of open models. Delivering state-of-the-art performance, Gemma 3 quickly established itself as a leading model capable of running on a single high-end GPU like the NVIDIA H100 using its native BFloat16 (BF16) precision.
Artificial Intelligence, Machine Learning, Hardware, Computer Vision, Open Source
597 points by emrah 6 days ago | 272 comments
Packing Input Frame Context in Next-Frame Prediction Models for Video Generation (lllyasviel.github.io)
Diffuse thousands of frames at full fps-30 with 13B models using 6GB laptop GPU memory. Finetune 13B video model at batch size 64 on a single 8xA100/H100 node for personal/lab experiments. Personal RTX 4090 generates at speed 2.5 seconds/frame (unoptimized) or 1.5 seconds/frame (teacache). No timestep distillation. Video diffusion, but feels like image diffusion.
Video Generation, Deep Learning, Computer Vision, Artificial Intelligence
269 points by GaggiX 7 days ago | 27 comments
SDFs from Unoriented Point Clouds Using Neural Variational Heat Distances (arxiv.org)
We propose a novel variational approach for computing neural Signed Distance Fields (SDF) from unoriented point clouds.
Machine Learning, Computer Vision, Neural Networks, Distance Fields
38 points by haxiomic 8 days ago | 5 comments
UniK3D: Universal Camera Monocular 3D Estimation (lpiccinelli-eth.github.io)
To address this, we present UniK3D, the first generalizable method for monocular 3D estimation able to model any camera.
Computer Vision, 3D Modeling, Machine Learning
46 points by rbanffy 8 days ago | 12 comments
Liquid: Language models are scalable and unified multi-modal generators (foundationvision.github.io)
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared feature space for both vision and language.
Generative AI, Language Models, Artificial Intelligence, Computer Vision
82 points by pr337h4m 10 days ago | 8 comments
LightlyTrain: Better Vision Models, Faster – No Labels Needed (github.com/lightly-ai)
LightlyTrain brings self-supervised pretraining to real-world computer vision pipelines, using your unlabeled data to reduce labeling costs and speed up model deployment.
Computer Vision, Machine Learning, AI, Self-Supervised Learning
30 points by michal-l 11 days ago | 11 comments
Watermark segmentation (github.com/Diffusion-Dynamics)
This repository by Diffusion Dynamics, showcases the core technology behind the watermark segmentation capabilities of our first product, clear.photo. This work leverages insights from research on diffusion models for image restoration tasks.
Image Processing, Computer Vision, Diffusion Models, Open Source
32 points by abriosi 11 days ago | 21 comments
Tom and Jerry One-Minute Video Generation with Test-Time Training (test-time-training.github.io)
Adding TTT layers into a pre-trained Transformer enables it to generate one-minute videos with strong temporal consistency and motion smoothness.
Generative AI, Computer Vision, Machine Learning, Deep Learning, Video Generation
80 points by walterbell 18 days ago | 18 comments
TripoSG – Text to 3D Model (github.com/VAST-AI-Research)
TripoSG is an advanced high-fidelity, high-quality and high-generalizability image-to-3D generation foundation model.
3D Modeling, Artificial Intelligence, Computer Vision, Machine Learning
30 points by taikon 20 days ago | 4 comments
No elephants: Breakthroughs in image generation (oneusefulthing.org)
Over the past two weeks, first Google and then OpenAI rolled out their multimodal image generation abilities. This is a big deal.
Generative AI, Image Generation, Artificial Intelligence, Computer Vision
445 points by Kerrick 21 days ago | 364 comments
Tenstorrent Launches Blackhole Developer Products at Tenstorrent Dev Day (tenstorrent.com)
Tenstorrent launched the next generation Blackhole™ chip family today at their DevDay event in San Francisco.
Hardware, AI, New Releases, Computer Vision
65 points by fidotron 22 days ago | 26 comments
QVQ-Max: Think with Evidence (qwenlm.github.io)
Last December, we launched QVQ-72B-Preview as an exploratory model, but it had many issues. Today, we are officially releasing the first version of QVQ-Max, our visual reasoning model.
Generative AI, Computer Vision, New Releases
121 points by wertyk 23 days ago | 26 comments
We Built an AI Tool to Create High-Quality 3D Models from Regular Videos (ycombinator.com)
We're a team of AI researchers passionate about simplifying 3D modeling. We've built an easy-to-use tool that generates detailed, high-quality 3D models directly from regular videos.
Artificial Intelligence, 3D Modeling, Computer Vision
14 points by unrealizex 23 days ago | 2 comments
Waymo's Foundation Model for Autonomous Driving with Drago Anguelov [video] (youtube.com)
Autonomous Driving, Artificial Intelligence, Machine Learning, Computer Vision, Waymo
5 points by xnx 23 days ago | 0 comments
Mirrors: The Blind Spot of Image and Video Generation Models (medium.com)
Recent advances in image generation models have demonstrated remarkable capabilities in creating photorealistic and imaginative visuals. However, a persistent challenge remains: accurately rendering reflections in mirrors.
Generative AI, Computer Vision, Image Generation, Artificial Intelligence
14 points by yamrzou 25 days ago | 3 comments
Apple's Cubify Anything: Scaling Indoor 3D Object Detection (github.com/apple)
This repository includes the public implementation of Cubify Transformer and the associated CA-1M dataset.
Computer Vision, Machine Learning, Apple
188 points by Tycho87 26 days ago | 27 comments
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 28 days ago | 10 comments
How DeepSeek Rewrote the Transformer [video] (youtube.com)
Transformers, Deep Learning, Computer Vision, Artificial Intelligence, Video
5 points by chetangole 29 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
71 points by smusamashah 29 days ago | 20 comments
VGGT: Visual Geometry Grounded Transformer (github.com/facebookresearch)
Computer Vision, Transformers, Artificial Intelligence, Deep Learning, Facebook Research
190 points by xnx 32 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 32 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 32 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 33 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 34 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 34 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 34 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 36 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 36 days ago | 0 comments