Pinned Repositories
CRNet
DiffHDR-pytorch
This is the official PyTorch implementation for DiffHDR: Towards High-quality HDR Deghosting with Conditional Diffusion Models (TCSVT'2023)
GaTector-A-Unified-Framework-for-Gaze-Object-Prediction
This repository is the official implementation of GaTector, which studies the newly proposed task, gaze object prediction. In this work, we build a novel framework named GaTector to tackle the gaze object prediction problem in a unified way. Particularly, a specific-general-specific (SGS) feature extractor is firstly proposed to utilize a shared backbone to extract general features for both scene and head images. To better consider the specificity of inputs and tasks, SGS introduces two input-specific blocks before the shared backbone and three task-specific blocks after the shared backbone. Specifically, a novel defocus layer is designed to generate object-specific features for object detection task without losing information or requiring extra computations. Moreover, the energy aggregation loss is introduced to guide the gaze heatmap to concentrate on the stared box. In the end, we propose a novel mDAP metric that can reveal the difference between boxes even when they share no overlapping area. Extensive experiments on the GOO dataset verify the superiority of our method in all three tracks, i.e., object detection, gaze estimation, and gaze object prediction.
HLNet
HLNet, which secured fourth place in the NTIRE 2024 Challenge on Bracketing Image Restoration and Enhancement - Track 2 BracketIRE+ Task, has now been accepted by the CVPR 2024 Workshop.
huTao1030's Repositories
huTao1030/DiffHDR-pytorch
This is the official PyTorch implementation for DiffHDR: Towards High-quality HDR Deghosting with Conditional Diffusion Models (TCSVT'2023)
huTao1030/CRNet
huTao1030/GaTector-A-Unified-Framework-for-Gaze-Object-Prediction
This repository is the official implementation of GaTector, which studies the newly proposed task, gaze object prediction. In this work, we build a novel framework named GaTector to tackle the gaze object prediction problem in a unified way. Particularly, a specific-general-specific (SGS) feature extractor is firstly proposed to utilize a shared backbone to extract general features for both scene and head images. To better consider the specificity of inputs and tasks, SGS introduces two input-specific blocks before the shared backbone and three task-specific blocks after the shared backbone. Specifically, a novel defocus layer is designed to generate object-specific features for object detection task without losing information or requiring extra computations. Moreover, the energy aggregation loss is introduced to guide the gaze heatmap to concentrate on the stared box. In the end, we propose a novel mDAP metric that can reveal the difference between boxes even when they share no overlapping area. Extensive experiments on the GOO dataset verify the superiority of our method in all three tracks, i.e., object detection, gaze estimation, and gaze object prediction.
huTao1030/HLNet
HLNet, which secured fourth place in the NTIRE 2024 Challenge on Bracketing Image Restoration and Enhancement - Track 2 BracketIRE+ Task, has now been accepted by the CVPR 2024 Workshop.