Sai Kumar Dwivedi

TokenHMR. [CVPR 2024] TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

InteractVLM. [CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

DSR. [ICCV 2021] DSR: Learning to Regress Bodies from Images using Differentiable Semantic Rendering

POCO. [3DV 2024] POCO: 3D Pose and Shape Estimation using Confidence

research-skills. Claude Code skills for AI/ML researchers

Object_Retrieval. Object Retrieval from Single Image (Used in InteractVLM & PICO, CVPR 2025)

dotfiles. Shell

PHALP. Code repository for the paper "Tracking People by Predicting 3D Appearance, Location & Pose". (CVPR 2022 Oral)

cx. Fast web-based file browser for files on HPC clusters