happyharrycn

DL-to-quantify-manipulation-activities-in-NICUs

Code release for "Deep Learning to Quantify Care Manipulation Activities in Neonatal Intensive Care Units"

LCSPCData

Dataset of measurements from a low-cost single-photon camera used in our CVPR 2024 paper "Towards 3D Vision with Low-Cost Single-Photon Cameras"

snag_release

Official Implementation of SnAG (CVPR 2024)

Foundation-Model_Multitask

HEPT

[ICML'24 Oral] LSH-Based Efficient Point Transformer (HEPT)

freecontrol

Official implementation of CVPR 2024 paper: "FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition"

eventful-transformer

Code for our paper "Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers"

actionformer_release

Code release for ActionFormer (ECCV 2022)

nlos3d

mRI

Data repo for mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors

ProcedureVRL

[CVPR 2023] Official code for "Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations"

INPL

UW-Madison-GI-Tract-Segmentation-Data-Tools

Code for MRI data de-identification and pakcaging

gadgetron-azure

Sample code for deploying Gadgetron image reconstruction in Azure

gadgetron

Gadgetron - Medical Image Reconstruction Framework

HIPT

Hierarchical Image Pyramid Transformer - CVPR 2022 (Oral)

Ego4D_NLQ_Actionformer

Ego4D_NLQ_Actionformer

using-U-net-to-restore-reconstruct-Fresnel-diffraction-images

I use U-net to reconstruct the fresnel diffraction images.

stable-diffusion

A latent text-to-image diffusion model

RegionCLIP

[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"

3d_photo_stylization

3D Photo Stylization

DeltaCNN

LiteReconfig_AE

TSP

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks (ICCVW 2021)

weak-sup-visual-grounding

The official implementation of CVPR 2021 Paper: Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation.

SGG_from_NLS

[ICCV 2021] Official code for "Learning to Generate Scene Graph from Natural Language Supervision"

DONERF

Code for "DONeRF Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks"

dsmil-wsi

DSMIL: Dual-stream multiple instance learning networks for tumor detection in Whole Slide Image

ApproxDet

Nystromformer