facebookresearch / co3d

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

#向量搜索引擎#向量相似性搜索库，为稠密向量提供高效相似度搜索和聚类

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Fairseq 是一个Python编写的 Seq2seq 建模工具包，可用于翻译、摘要、语言建模和其他文本生成任务训练自定义模型

DUSt3R: Geometric 3D Vision Made Easy

TripoSR: Fast 3D Object Reconstruction from a Single Image

#大语言模型#Scalable data pre processing and curation toolkit for LLMs

Open-Sora： 完全开源的高效复现类Sora视频生成方案

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in authentic surroundings. (CVPR2024).

A curated list of awesome neural radiance fields papers

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

#计算机科学#[3DV'24 Best Paper Honorable Mention] NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM

#计算机科学#One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more

DeepSeek-VL: Towards Real-World Vision-Language Understanding

#计算机科学#Code and data for "AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks" [TMLR 2024]

The open source mesh processing system

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Layer Diffuse custom nodes

Official implementation of "ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models".

大模型Grok-1开源