Open-source alternatives to LovaszSoftmax

Angjoo Kanazawa \ , Shubham Tulsiani \ , Alexei A. Efros, Jitendra Malik

Project page for End-to-end Recovery of Human Shape and Pose

This repository contains the TensorFlow code for our NeurIPS 2018 paper “Unsupervised Attention-guided Image-to-Image Translation”. This code is based on the TensorFlow implementation of CycleGAN provided by Harry Yang. You may need to train several times as the quality of the results are…

Official implementation of GANimation. In this work we introduce a novel GAN conditioning scheme based on Action Units (AU) annotations, which describe in a continuous manifold the anatomical facial movements defining a human expression. Our approach permits controlling the magnitude of…

Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.

The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)

Attention-based Deep Multiple Instance Learning

记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文

3DMV jointly combines RGB color and geometric information to perform 3D semantic segmentation of RGB-D scans. This work is based on our ECCV'18 paper, 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation.

CVPR2018: Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatio-temporal Patterns

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image

Code for PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

"Zero-Shot" Super-Resolution using Deep Internal Learning

Multi-Content GAN for Few-Shot Font Style Transfer at CVPR 2018

Code for our CVPR 2018 paper: "Synthesizing Images of Humans in Unseen Poses"

This is the implementation of Hierarchical Long-term Video Prediction without Supervision, to be published in ICML 2018.

Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"

CVPR 2025 Highlight X-Dyna: Expressive Dynamic Human Image Animation

CVPR 2025 🔥 Official impl. of "TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation".

This is re-implementation of "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices"

PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

This project is a deep learning computer vision implementation focused on low-light image restoration. It uses a neural network to process raw sensor data, mapping underexposed images to well-exposed versions to improve visibility and restore natural colors. The implementation is based on CVPR 2018 research and utilizes TensorFlow to execute the computational graph. It employs a convolutional neural network and pixel-wise regression to reconstruct scene lighting directly from unprocessed raw image data. The project includes a framework for supervised pair learning, where models are trained u

Code for the ECCV 2018 paper "Pairwise Confusion for Fine-Grained Visual Classification"