Abhinaba Bala 's Projects
Semantic Segmentation Architectures Implemented in PyTorch
A minimalistic boiler plate code for training pytorch models
3D transformations for Python
Python programs, usually short, of considerable difficulty, to perfect particular skills.
PyViz3D is a web-based visualizer for 3D objects and point clouds.
website for generating random quotes
Solving Partial Assignment Problems using Random Clique Complexes, ICML 2018
A simple renderer with z-buffer for synthesis data generating.
Official Pytorch implementation of RePOSE (ICCV2021)
Basically listing out how to get some basic logistics out of the way
Graphics Programming Resources List
RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization, CVPR 2022
one-click deepfake (face swap)
Coder for "On the Continuity of Rotation Representations"
Robust Self-supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling, IEEE Robotics and Automation Letters (RA-L) (presented at ICRA 2022)
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Stochastic Scene-Aware Motion Prediction https://samp.is.tue.mpg.de/
Single Headed Attention RNN - "Stop thinking with your head"
SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation
Finding the source code hidden in the text.
Official Tensorflow implementation of SilhoNet
simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.
Weirdly challenging Simple MLP overfitting problem
Single-Stage 6D Object Pose Estimation, CVPR 2020
Code repository for the paper "Improving End-to-End SLU performance with Prosodic Attention and Distillation" accepted at Interspeech 2023.
NumPy, TensorFlow and PyTorch implementation of human body SMPL model and infant body SMIL model.
SMPL-X
This add-on allows you to add SMPL-X skinned meshes to your current Blender scene. Each imported SMPL-X mesh consists of a shape specific rig, as well as shape keys (blend shapes) for shape, expression and pose correctives.