Search Results for "visual"

CogVLM is an open-source visual–language model suite—and its GUI-oriented sibling CogAgent—aimed at image understanding, grounding, and multi-turn dialogue, with optional agent actions on real UI screenshots. The flagship CogVLM-17B combines ~10B visual parameters with ~7B language parameters and supports 490×490 inputs; CogAgent-18B extends this to 1120×1120 and adds plan/next-action outputs plus grounded operation coordinates for GUI tasks.

The codebase was designed to help researchers and practitioners quickly reproduce FAIR’s results and leverage robust pre-trained backbones for downstream tasks. It also integrates Gradient Blending, an audio-visual modeling method that fuses modalities effectively (available in the Caffe2 implementation). Although VMZ is now archived and no longer actively maintained, it remains a valuable reference for understanding early large-scale video model training, transfer learning, and multimodal integration strategies that influenced modern architectures like SlowFast and X3D.

VGGSfM is an advanced structure-from-motion (SfM) framework jointly developed by Meta AI Research (GenAI) and the University of Oxford’s Visual Geometry Group (VGG). It reconstructs 3D geometry, dense depth, and camera poses directly from unordered or sequential images and videos. The system combines learned feature matching and geometric optimization to generate high-quality camera calibrations, sparse/dense point clouds, and depth maps in standard COLMAP format. Version 2.0 adds support for dynamic scene handling, dense point cloud export, video-based reconstruction (1000+ frames), and integration with Gaussian Splatting pipelines. ...

VisualGLM-6B is an open-source multimodal conversational language model developed by ZhipuAI that supports both images and text in Chinese and English. It builds on the ChatGLM-6B backbone, with 6.2 billion language parameters, and incorporates a BLIP2-Qformer visual module to connect vision and language. In total, the model has 7.8 billion parameters. Trained on a large bilingual dataset — including 30 million high-quality Chinese image-text pairs from CogView and 300 million English pairs — VisualGLM-6B is designed for image understanding, description, and question answering. Fine-tuning on long visual QA datasets further aligns the model’s responses with human preferences. ...

ImageReward is the first general-purpose human preference reward model (RM) designed for evaluating text-to-image generation, introduced alongside the NeurIPS 2023 paper ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation. Trained on 137k expert-annotated image pairs, ImageReward significantly outperforms existing scoring methods like CLIP, Aesthetic, and BLIP in capturing human visual preferences. It is provided as a Python package (image-reward) that enables quick scoring of generated images against textual prompts, with APIs for ranking, scoring, and filtering outputs. Beyond evaluation, ImageReward supports Reward Feedback Learning (ReFL), a method for directly fine-tuning diffusion models such as Stable Diffusion using human-preference feedback, leading to demonstrable improvements in image quality.

A series of open source files and programs available to use for developing programs to work with the WowWee Robotics RSMedia Robot. These include a USB serial console, a cross-compiler, a firmware dump program, text-to-speech and source code.

AI File Sorter is a cross-platform desktop application that uses AI to organize all files and suggest better file names for image files, based on their visual content. The app can analyze picture files locally and suggest meaningful, human-readable names. For example, a generic file like IMG_2048.jpg can be renamed to clouds_over_lake.jpg. All rename and categorization suggestions are optional and must be reviewed and approved before anything is applied. AI File Sorter helps tidy up cluttered folders such as Downloads, external drives, or NAS storage by grouping files based on filenames, extensions, folder context, and learned organization patterns. ...

...During inference, the model fine-tunes itself to align with the geometric constraints of a specific input video, ensuring stable and realistic depth maps even in less-constrained regions. This approach achieves improved geometric consistency and visual stability compared to prior monocular reconstruction methods. The project can process challenging hand-held video footage, including those with moderate dynamic motion, making it practical for real-world usage.

...Each environment contains detailed models of real-world spaces, including rooms, furniture, glass, and mirror surfaces. The dataset also provides semantic and instance segmentations, planar decomposition, and navigation meshes, making it highly suitable for simulation, visual perception, and autonomous navigation tasks. Replica integrates seamlessly with AI Habitat, Meta’s framework for embodied AI training, enabling large-scale agent simulation and photorealistic rendering for reinforcement learning and robotics. Researchers can use Replica’s ReplicaViewer to interactively explore the 3D scenes.

DTW is intended to be a Voice in -> Pictures + Text out program written in java using Sphinx from CMU. This is intended to be useful to people who have good oral/visual literacy skills but poor written literacy skills.