GitHub

[ICME2025] From 2D images to 3D model: Weakly Supervised Multi-View Face Reconstruction with Deep Fusion

For 3090: We recommend CUDA 11.1 & Python v3.8.10 & Pytorch 1.9.0 conda create -n dfnet python=3.8.10 source activate dfnet conda install -c conda-forge cudatoolkit=11.1 cudnn=8.1.0 conda install -c ...
IEEE

AMANet: Adaptive Multi-Path Aggregation for Learning Human 2D-3D Correspondences

Abstract: Learning human 2D-3D correspondences aims to map all human 2D pixels to a 3D human template, namely human densepose estimation, involving surface patch recognition (i.e., Index-to-Patch (I)) ...
IEEE

Learning Joint 2D-3D Representations for Depth Completion

Abstract: In this paper, we tackle the problem of depth completion from RGBD data. Towards this goal, we design a simple yet effective neural network block that learns to extract joint 2D and 3D ...
Gizmochina

XREAL 1S is the world’s first AR glasses with automatic 2D-to-3D video conversion

XREAL is wrapping up 2025 with the launch of a new entry-level AR glasses model, the XREAL 1S. It sits below the more expensive XREAL One Pro (announced in July) in the lineup and is the first in the ...