The official repository for the "Uncertainty Visualization via Low-Dimensional Posterior Projections" paper

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)

[CVPR'23 Best Paper Award] Planning-oriented Autonomous Driving

Poisson Surface Reconstruction

GPT Meet Zotero.

Framework for Easily Invertible Architectures

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

Open-source framework for uncertainty and deep learning models in PyTorch 🌱

Documentation of the TorchUncertainty library.

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Official PyTorch implementation of End-to-end 3D Tracking with Decoupled Queries [ICCV 2023]

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

OpenMMLab's next-generation platform for general 3D object detection.

High-quality implementations of standard and SOTA methods on a variety of tasks.

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Uncertainty-aware representation learning (URL) benchmark

Official implementation of Adabins: Depth Estimation using adaptive bins

The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching

Pytorch framework for doing deep learning on point clouds.

pix2tex: Using a ViT to convert images of equations into LaTeX code.

OpenMMLab Detection Toolbox and Benchmark

ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models

(ICLR) Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

OpenMMLab Computer Vision Foundation

CVPR2023-Occupancy-Prediction-Challenge

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.