Stars
An unified model for 4D human-scene reconstruction
A simple state update rule to enhance length generalization for CUT3R
an implementation of 3D Ken Burns Effect from a Single Image using PyTorch
ViPE: Video Pose Engine for Geometric 3D Perception
Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures
[CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models
Official Repository for ICCV 2025 paper DAViD: Modeling Dynamic Affordance of 3D Objects using Pre-trained Video Diffusion Models
Official implementation of ICCV 2025 paper - CharaConsist: Fine-Grained Consistent Character Generation
A challenging dataset used for one-shot face sketch synthesis research
[ICCV 2025 ⭐highlight⭐] Implementation of VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework
[Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Lets make video diffusion practical!
[ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.
Codebase for "VLMaterial: Procedural Material Generation with Large Vision-Language Models"
A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
[ICCV 2025 Highlight] ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
Official implementation for ICLR'25 paper "LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh"
Official implementation of SwiftSketch
Align Anything: Training All-modality Model with Feedback
Pippo: High-Resolution Multi-View Humans from a Single Image
FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation