Photometric optimization code for creating the FLAME texture space and other applications

Official Pytorch Implementation of 3DV2021 paper: SAFA: Structure Aware Face Animation.

a Pytorch library for multi-view 3D understanding and generation

[ICCV 2023 Oral] Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image

Differentiable Point Radiance Fields Rasteriser for Novel View Synthesis

Deform meshes by reinforcement learning

Code for the CubeRefine R-CNN model of our CVPRW '23 paper "Parcel3D: Shape Reconstruction From Single RGB Images for Applications in Transportation Logistics".

Code to construct textured deformed SMPL-X meshes for HUMBI data

Виртуальная примерка 3D модели одежды на видео (что-то в духе Clometrica)

Pose refinement with differentiable rendering

PyTorch implementation of the human neural rendering in unseen positions presented at WACV 2022 "Creating and Reenacting Controllable 3D Humans with Differentiable Rendering"

Gmesh supports differentiable rendering of mixed 3D Gaussians and meshes within a single scene.

Implementing a PointNet based architecture for classification and segmentation with point clouds. Q1 and Q2 focus on implementing, training and testing models. Q3 asks you to quantitatively analyze model robustness.

Official Code of ACM MM'24 Paper "Unsupervised Multi-view Pedestrian Detection"

This project shows the basic of 3D vision which involves mesh, point cloud and voxel grid. The first part is about transforming 2D data into 3D.

GUI to view current mesh during render using pytorch3d.

Exploring the types of losses and decoder functions for regressing to voxels, point clouds, and mesh representations from single view RGB input.

Official PyTorch implementation of BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025). BLADE tackles close-range human mesh recovery where perspective distortion is strongest, and solves for camera pose and focal length in addition to SMPL(-X) parameters.

Covering 3D computer vision concepts and implementations from state-of-the-art papers and architectures

Implementation of Canonical Surface Mapping (https://github.com/nileshkulkarni/csm) using PyTorch and Pytorch3D