View synthesis for the public.

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

My portfolio powered by Next.js, content sourced from Notion, styled with Tailwind CSS and deployed on Vercel. 🙌

3D Reconstruction with Spatial Memory

🚀 Nextjs Blog Boilerplate is starter code for your blog based on Next framework. ⚡️ Made with Nextjs 12, TypeScript, ESLint, Prettier, PostCSS, Tailwind CSS 3.

Web-based 3D visualization + Python

[SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums

The open curriculum for learning web development

A quick guide (especially) for trending instruction finetuning datasets

News: the 10k dataset is ready for download.

VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

Self-hosted game stream host for Moonlight.

[BMVC 2024 ] Drone-assisted Road Gaussian Splatting with Cross-view Uncertainty

The first open-source system for large-scale scene reconstruction training and rendering.

This is the official reproduction of FancyVideo.

GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splatting

Pytorch implementation of Pano2Room (SIGGRAPH Asia 2024)

Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

StableDelight: Real-Time Reflection Removal from Textured Surfaces

About The official implementation of the paper "Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network“. (ECCV 2024)

High-resolution models for human tasks.

Official code of "LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation"

Rich is a Python library for rich text and beautiful formatting in the terminal.

[CVPR 2024] Official repository of "Material Palette: Extraction of Materials from a Single Real-world Image"

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

[ECCV2024 Oral] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

Implementation of DisCo:Diffusion-based Cross-modal Shape Reconstruction from LASA (CVPR2024)

We present Object Images (Omages): An homage to the classic Geometry Images.