Search Results for "pixel"
Sort By:
Showing 23 open source projects for "pixel"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
...Because the objective is non-autoregressive and operates in embedding space, JEPA tends to be compute-efficient and stable at scale. The approach has become a strong alternative to contrastive or pixel-reconstruction methods for representation learning. -
2
vJEPA-2
PyTorch code and models for VJEPA2 self-supervised learning from video
...Instead of reconstructing pixels, it predicts the missing high-level embeddings of masked space-time regions using a context encoder and a slowly updated target encoder. This objective encourages the model to learn semantics, motion, and long-range structure without the shortcuts that pixel-level losses can invite. The architecture is designed to scale: spatiotemporal ViT backbones, flexible masking schedules, and efficient sampling let it train on long clips while remaining stable. Trained representations transfer well to downstream tasks such as action recognition, temporal localization, and video retrieval, often with simple linear probes or light fine-tuning. ... -
3
EasyOCR
Ready-to-use OCR with 80+ supported languages
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc. EasyOCR is a python module for extracting text from image. It is a general OCR that can read both natural scene text and dense text in document. We are currently supporting 80+ languages and expanding. Second-generation models: multiple times smaller size, multiple times faster inference, additional characters and comparable accuracy to the first... -
4
Agent Sprite Forge
Agent Skill for generating 2D sprite sheets and map, transparent PNG
...The project functions as an “agent skill” that can integrate with coding assistants and AI workflows to automate parts of the game asset creation pipeline. It focuses on generating production-friendly pixel art and animation assets that can be used in indie games, prototypes, and rapid iteration workflows. The system supports multi-frame sprite generation, animation sequencing, and transparent background rendering for easier integration into game engines. Its architecture is designed around automation and repeatability, enabling developers to generate large batches of visual assets through structured prompt workflows. ... -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
5
PixelRAG
The beginning of scalable pixel-native search
PixelRAG is a visual retrieval-augmented generation system that searches documents by how they look, not only by the text they contain. It renders web pages, PDFs, and images into screenshot tiles, then performs retrieval over those visual representations. This approach preserves layout, tables, charts, diagrams, infographics, and other visual structure that traditional HTML or text parsing can miss. The project includes tools for rendering, chunking, embedding, indexing, and serving visual... -
6
AndroidEnv
RL research on Android devices
android_env is a reinforcement learning (RL) environment developed by Google DeepMind that enables agents to interact with Android applications directly as a learning environment. It provides a standardized API for training agents to perform tasks on Android apps, supporting tasks ranging from games to productivity apps, making it suitable for research in real-world RL settings. -
7
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Stable Diffusion
Grounded-Segment-Anything is a research-oriented project that combines powerful open-set object detection with pixel-level segmentation and subsequent creative workflows, effectively enabling detection, segmentation, and high-level vision tasks guided by free-form text prompts. The core idea behind the project is to pair Grounding DINO — a zero-shot object detector that can locate objects described by natural language — with Segment Anything Model (SAM), which can produce detailed masks for objects once they are localized. ... -
8
Map-Anything
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
...Instead of stitching together many task-specific models, it uses a single architecture that supports a wide range of 3D tasks—multi-image structure-from-motion, multi-view stereo, monocular metric depth, registration, depth completion, and more. The model flexibly accepts different input combinations (images, intrinsics, poses, sparse or dense depth) and produces a rich set of outputs including per-pixel 3D points, camera intrinsics, camera poses, ray directions, confidence maps, and validity masks. Its inference path is fully feed-forward with optional mixed-precision and memory-efficient modes, making it practical to scale to long image sequences while keeping latency predictable. -
9
LISA
LISA: Reasoning Segmentation via Large Language Model
LISA is an open-source multimodal AI system designed to enable language models to perform pixel-level reasoning and segmentation tasks on images. The project introduces a framework where a large language model can interpret natural language instructions and produce segmentation masks that highlight relevant regions in an image. Instead of relying solely on predefined object categories, the model is capable of reasoning about complex textual queries and translating them into visual segmentation outputs. ... -
Compliant and Reliable File Transfers Backed by Top Security CertificationsStop relying on non-certified, legacy file transfer tools that creak under the weight of modern security demands. Get full audit trails, advanced access controls and more supported by an award-winning team of experts. Start your free 25-day trial today.
-
10
StarVector
StarVector is a foundation model for SVG generation
...This approach allows StarVector to create scalable graphics that maintain visual quality regardless of resolution, which is especially useful for design tools and illustration workflows. Because the model produces SVG code rather than pixel images, the output can be edited programmatically or integrated directly into web and design environments. -
11
Sa2VA
Official Repo For "Sa2VA: Marrying SAM2 with LLaVA
...With minimal instruction tuning (often one-shot), Sa2VA can handle tasks such as “segment the main subject,” “what are the objects in this scene?”, or “track this object through the video,” outputting pixel-perfect masks or spoken/textual answers as appropriate. -
12
FLUX.1 Krea
Powerful open source image generation model
FLUX.1 Krea [dev] is an open-source 12-billion parameter image generation model developed collaboratively by Krea and Black Forest Labs, designed to deliver superior aesthetic control and high image quality. It is a rectified-flow model distilled from the original Krea 1, providing enhanced sampling efficiency through classifier-free guidance distillation. The model supports generation at resolutions between 1024 and 1280 pixels with recommended inference steps between 28 and 32 for optimal... -
13
Recurrent Interface Network (RIN)
Implementation of Recurrent Interface Network (RIN)
...The big surprise is that the generations can reach this level of fidelity. Will need to verify this on my own machine. Additionally, we will try adding an extra linear attention on the main branch as well as self-conditioning in the pixel space. The insight of being able to self-condition on any hidden state of the network as well as the newly proposed sigmoid noise schedule are the two main findings. -
14
CoTracker
CoTracker is a model for tracking any point (pixel) on a video
...By reasoning about all tracks together, it can maintain temporal consistency, handle mutual occlusions, and reduce identity swaps when trajectories cross. The model takes sparse point queries on one frame and predicts their sub-pixel locations and a visibility score for every subsequent frame, producing long, coherent trajectories. Its transformer-style architecture aggregates information both along time and across points, allowing it to recover tracks even after brief disappearances. The repository ships with inference scripts, pretrained weights, and simple interfaces to seed points, run tracking, and export trajectories for downstream tasks. ... -
15
PIFuHD
High-Resolution 3D Human Digitization from A Single Image
PIFuHD (Pixel-Aligned Implicit Function for 3D human reconstruction at high resolution) is a method and codebase to reconstruct high-fidelity 3D human meshes from a single image. It extends prior PIFu work by increasing resolution and detail, enabling fine geometry in cloth folds, hair, and subtle surface features. The method operates by learning an implicit occupancy / surface function conditioned on the image and camera projection; at inference time it queries dense points to reconstruct a mesh via marching cubes. ... -
16
min(DALL·E)
min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
...The largest logit is subtracted from the logits to avoid infs. The logits are then divided by the temperature. If is_seamless is true, the image grid will be tiled in token space not pixel space. -
17
Mask2Former
Code release for "Masked-attention Mask Transformer
...Its core idea is to cast segmentation as mask classification: a transformer decoder predicts a set of mask queries, each with an associated class score, eliminating the need for task-specific heads. A pixel decoder fuses multi-scale features and feeds masked attention in the transformer so each query focuses computation on its current spatial support. This leads to accurate masks with sharp boundaries and strong small-object performance while remaining efficient on high-resolution inputs. The project provides extensive configurations and pretrained models across popular benchmarks like COCO, ADE20K, and Cityscapes. ... -
18
Fashion-MNIST
A MNIST-like fashion product database
Fashion-MNIST is an open-source dataset created by Zalando Research that provides a standardized benchmark for image classification algorithms in machine learning. The dataset contains grayscale images of fashion products such as shirts, shoes, coats, and bags, each labeled according to its clothing category. It was designed as a direct replacement for the original MNIST handwritten digits dataset, maintaining the same structure and image size so that researchers could easily switch datasets... -
19
CIPS-3D
3D-aware GANs based on NeRF (arXiv)
3D-aware GANs based on NeRF (arXiv). This repository contains the code of the paper, CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis. The problem of mirror symmetry refers to the sudden change of the direction of the bangs near the yaw angle of pi/2. We propose to use an auxiliary discriminator to solve this problem. Note that in the initial stage of training, the auxiliary discriminator must dominate the generator more than the main discriminator does. ... -
20
MaskFormer
Per-Pixel Classification is Not All You Need for Semantic Segmentation
MaskFormer is a unified framework for image segmentation developed by Facebook Research, designed to bridge the gap between semantic, instance, and panoptic segmentation within a single architecture. Unlike traditional segmentation pipelines that treat these tasks separately, MaskFormer reformulates segmentation as a mask classification problem, enabling a consistent and efficient approach across multiple segmentation domains. Built on top of Detectron2, it supports a wide range of datasets... -
21
DensePose
A real-time approach for mapping all human pixels of 2D RGB images
DensePose is a computer vision system that maps all human pixels in an RGB image to the 3D surface of a human body model. It extends human pose estimation from predicting joint keypoints to providing dense correspondences between 2D images and a canonical 3D mesh (such as the SMPL model). This enables detailed understanding of human shape, motion, and surface appearance directly from images or videos. The repository includes the DensePose network architecture, training code, pretrained... -
22
Image GPT
Large-scale autoregressive pixel model for image generation by OpenAI
...While the repository is archived and provided as-is, it remains a valuable starting point for experimenting with autoregressive transformers applied directly to raw pixel data. By demonstrating GPT’s flexibility across modalities, Image-GPT influenced subsequent multimodal generative research. -
23
Universe Starter Agent
A starter agent that can solve a number of universe environments
...Its purpose is to serve as a baseline or reference implementation so researchers or developers can see how to build agents that operate in real-time, visual environments (e.g., games, browser apps) via pixel observations and keyboard/mouse actions. Under the hood, this starter agent implements a version of the A3C (Asynchronous Advantage Actor-Critic) algorithm, adapted for the specific challenges of Universe environments (e.g., network latency, VNC streaming, asynchronous observations). The repo includes modules like train.py, worker.py, model.py, a3c.py, and envs.py to support training, parallel worker management, policy/critics, and environment wrappers.
- Previous
- You're on page 1
- Next
