MAT: Mask-Aware Transformer for Large Hole Image Inpainting

SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance

CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner

Official code repository of "UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis", ICCV 2025.

This repository catalogs the papers I referenced while completing a project on point cloud completion using diffusion.

Official code of "Lightweight 3D Gaussian Splatting Compression via Video Codec"

[NeurIPS 2025] LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

"CF3: Compact and Fast 3D Feature Fields" (ICCV 2025)

[SIGGRAPH ASIA 2025] Code for PartUV: Part-Based UV Unwrapping of 3D Meshes

GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting

GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors

Official Release of ICCV 2025 paper -- DiscretizedSDF

WebGPU implementation for the radix sort algorithm as described in the paper "Fast 4-way parallel radix sorting on GPUs"

[Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Paper "DeepMill: Neural Accessibility Learning for Subtractive Manufacturing". ACM SIGGRAPH 2025 (Conference track).

[NeurIPS 2025] Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

[CVPR 2025] DTGBrepGen: A Novel B-rep Generative Model through Decoupling Topology and Geometry

High-Fidelity Lightweight Mesh Reconstruction from Point Clouds (CVPR 2025 Highlight)

Implementation of the paper: "Adaptive Remeshing for Real-Time Mesh Deformation"

A Modular Framework for 3D Generation and Beyond [WIP]

CUDA 算子手撕与面试指南

Differentiable estimations of curvatures and topology for 3D shapes