#3d-vision
Showing 44 of 44 repositories tagged #3d-vision, ranked by stars
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
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
[ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
Bundler Structure from Motion Toolkit
🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)
A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.
Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.
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
News: the 10k dataset is ready for download.
[ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
Volumetric Human Teleportation (SIGGRAPH 2020 Real-Time Live) Monocular Real-Time Volumetric Performance Capture(ECCV 2020)
Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral
Current state of supervised and unsupervised depth completion methods
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration
Code and models for our ICCV 2021 paper "MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis"
🔥3D-BoNet in Tensorflow (NeurIPS 2019, Spotlight)
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
Official Code for ECCV 2022 paper "AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing"
Orbbec SDK v1&v2 Pre-Compiled Repo
Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.
Official source code of Fast Point Transformer, CVPR 2022
A curated list of tutorials, papers, software related to multi-view stereo.
[CVPR 2024 Highlight] Official repository for paper "SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction"
DeepI2P: Image-to-Point Cloud Registration via Deep Classification. CVPR 2021
Awesome Resources for Advanced Computer Vision Topics
Pytorch code for ICCV'23 paper. NEO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes
Official code for NeurIPS2023 paper CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection and TPAMI 2025 paper CoDAv2
This repository contains code for the tracking system as described in ''Combined Image- and World-Space Tracking in Traffic Scenes'', ICRA 2017.
[3DV 2022] The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs
MinkLoc3Dv2: Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training
TUM Traffic Dataset Development Kit
A graphical user interface to annotate point clouds and 3D data.
Human Performance Capture from Monocular Video in the Wild (3DV2021)
Code accompanying the paper "Layer-structured 3D Scene Inference via View Synthesis", ECCV 2018
Segment Any 4D Gaussians
Person Following Robot - Smart Trolley
Fast Neural Scene Flow (ICCV 2023)
Code for our ICCV 19 paper : Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale
Learning low-shot object classification with explicit shape bias learned from point clouds
Experimental repo for modelling Articulated Object Neural Radiance Field