This is the implementation of the paper "FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object Detection" (ECCV 2024)

Official repository for "AM-RADIO: Reduce All Domains Into One"

The programs for generating the 40k hair dataset in HairNet: Single-View Hair Reconstruction using Convolutional Neural Networks https://arxiv.org/abs/1806.07467

State-of-the-art 2D and 3D Face Analysis Project

Evaluation of feature extraction methods for query-by-example spoken term detection with low resource languages

Function to frontalize non-frontal 2D facial landmarks generated from the DLIB library

The source code for paper "Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model".

Implementation for our paper Breaking the Cycle - Colleagues are all you need (CVPR 2020)

3D face reconstruction from monocular image via deep convolutional neural networks and differentiable ray tracing

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

Line-based PatchMatch MVS (LPMVS)

(CVPR 2022) HairMapper: Removing Hair from Portraits Using GANs.

Pytorch implementation of convolutional neural network visualization techniques

🌕 [ICCV 2021] Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection. A self-supervised learning way for low-light image object detection.

Python implementation of Point Feature Histogram (PFH) from PCL

MOT using deepsort and yolov3 with pytorch

Joint Embeddings of Shapes and Images via CNN Image Purification

Kernel Point Convolutions

COCO 2018 Panoptic Segmentation Task API (Beta version)