Search Results for "structure"

COLMAP is a general-purpose Structure-from-Motion (SfM) and Multi-View Stereo (MVS) pipeline with a graphical and command-line interface. It offers a wide range of features for the reconstruction of ordered and unordered image collections. The software is licensed under the new BSD license.

VGGT is a transformer-based framework aimed at unifying classic visual geometry tasks—such as depth estimation, camera pose recovery, point tracking, and correspondence—under a single model. Rather than training separate networks per task, it shares an encoder and leverages geometric heads/decoders to infer structure and motion from images or short clips. The design emphasizes consistent geometric reasoning: outputs from one head (e.g., correspondences or tracks) reinforce others (e.g., pose or depth), making the system more robust to challenging viewpoints and textures. The repo provides inference pipelines to estimate geometry from monocular inputs, stereo pairs, or brief sequences, together with evaluation harnesses for common geometry benchmarks. ...

...The repository provides a roadmap, references, teaching materials, and sometimes the author’s own project examples, offering both guidance and community support. Because the CS field is broad, the structure helps learners allocate study time, avoid duplication, and benefit from “best in class” resources instead of randomly browsing.

...It revisits classic ResNet-style backbones through the lens of transformer design trends—large kernel sizes, inverted bottlenecks, layer normalization, and GELU activations—to bridge the performance gap between convolutions and attention-based models. ConvNeXt’s clean, hierarchical structure makes it efficient for both pretraining and fine-tuning across a wide range of visual recognition tasks. It achieves competitive or superior results on ImageNet and downstream datasets while being easier to deploy and train than transformers. The repository provides pretrained models, training recipes, and ablation studies demonstrating how incremental design choices collectively yield state-of-the-art performance.

...The framework provides a complete training and evaluation pipeline for human pose estimation using a cascaded pyramid network (CPN). OpenCE leverages a feature pyramid structure combined with a refinement stage to improve keypoint detection accuracy across multiple scales, particularly for challenging poses in crowded scenes. The repository includes training scripts, pretrained models, and testing code, allowing users to reproduce results reported in the paper. It supports standard human pose estimation benchmarks such as COCO, with configurations optimized for accuracy and efficiency. ...

OpenCV bindings for Node.js. OpenCV is the defacto computer vision library - by interfacing with it natively in node, we get powerful real time vision in js. People are using node-opencv to fly control quadrocoptors, detect faces from webcam images and annotate video streams. If you're using it for something cool, I'd love to hear about it! You'll need OpenCV 2.3.1 or newer installed before installing node-opencv. You can use opencv to read in image files. Supported formats are in the OpenCV...

A proximity forest is a data structure that allows for efficient computation of approximate nearest neighbors of arbitrary data elements in a metric space. See: O'Hara and Draper, "Are You Using the Right Approximate Nearest Neighbor Algorithm?", WACV 2013 (best student paper award). One application of a ProximityForest is given in the following CVPR publication: Stephen O'Hara and Bruce A.