Shape and Pose Annotations for the Objects in the ScanNet++ dataset.

Factor graphs with Ceres in Python

[CVPR 2026] PhysHead: Simulation-Ready Gaussian Head Avatars

[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

[3DV'24] GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar

Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024

✨✨Latest Advances on Multimodal Large Language Models

Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

Mamba SSM architecture

[ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

Official code repository of "HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion" @ ICCV 2023

Using Low-rank adaptation to quickly fine-tune diffusion models.

Support BlenderProc2 with multi-GPU batch rendering and 3D visualization for 3D-Front

[CVPR 2024] DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis

Metric depth estimation from a single image

General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

[CVPR23 Highlight] Implementation for Panoptic Lifting

Official code of the paper The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"

[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration

[ECCV 2022] TAFIM: Targeted Adversarial Attacks against Facial Image Manipulation

This is the official code for "Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories"

[CVPR 2022 Oral] Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

Some scripts for GNOME Nautilus that simplify working with files. Particularly useful for ML and other applications.

Implementation of ECCV'2022: Pose2Room: Understanding 3D Scenes from Human Activities

This repo accompanies the research paper, ARKitScenes - A Diverse Real-World Dataset for 3D Indoor Scene Understanding Using Mobile RGB-D Data and contains the data, scripts to visualize and proces…

[ICCV21] Code for "RetrievalFuse: Neural 3D Scene Reconstruction with a Database"