3d-vision

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

[ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior

An Invitation to 3D Vision: A Tutorial for Everyone

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Bundler Structure from Motion Toolkit

🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.

[NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

Implementation of DynIBaR Neural Dynamic Image-Based Rendering (CVPR 2023)

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis

Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)

「3D视觉(三维重建、SLAM、AR/VR) + 传统图像处理 + 计算机视觉(偏AI) 」重要知识点和面试问题。