Official implementation of "HowToCaption: Prompting LLMs to Transform Video Annotations at Scale." ECCV 2024

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text" (NeurIPS 2024).

[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacch…

3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

[ECCV 2024 Oral] ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

Code for SIGGRAPH2024 paper "ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations"

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

A collection of 1,000+ emoji for Slack

Existing emoji lack sufficient dank

Think of this like a Slack custom emoji starter kit except it includes emoji of a weirdly specific subset of my friends.

Custom icon collection for slack reaction

CVPR 2020 - On the uncertainty of self-supervised monocular depth estimation

[ECCV'24] On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy

Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from images to 3D grids.

Repository for "CoMix: Comprehensive Benchmark for Multi-Task Comic Understanding"

SecMI on Latent Diffusion Model (LDM)

🤖 Machine Learning Summer School deadlines

CVPR2023 | MVImgNet: A Large-scale Dataset of Multi-view Images

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

Google's Operations Research tools:

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation