Benjamin Biggs

SMALify. This repository contains an implementation for performing 3D animal (quadruped) reconstruction from a monocular image or video. The system adapts the pose (limb positions) and shape (animal type/height/weight) parameters for the SMAL deformable quadruped model, as well as camera parameters until the projected SMAL model aligns with 2D keypoints and silhouette segmentations extracted from the input frame(s).

StanfordExtra. 12k labelled instances of dogs in-the-wild with 2D keypoint and segmentations. Dataset released with our ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

WLDO. Code for paper ECCV 2020 paper: Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop.

BADJA. Benchmark Animal Dataset of Joint Annotations (BADJA) with example code, as introduced in "Creatures Great and SMAL: Recovering the shape and motion of animals from video" (ACCV 2018).

SMALViewer. PyQt5 app for viewing SMAL meshes

3D-Multibodies. Code for paper 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

DeepMini. A repository of mini versions for popular deep networks.

SMALify_Dev. Python

CreaturesResult. Scripts for viewing Creatures Great and SMAL results.

Sweepstakes. Code to run the sweepstake for World Cup 22

whole-foods-mcp. MCP server for automating Whole Foods grocery ordering via Claude Code