[CVPR 2025] VGGT: Visual Geometry Grounded Transformer

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Official PyTorch implementation for "Large Language Diffusion Models"

Personal Webpage with curated AI conference deadlines: https://nunoduarte.github.io

[ICCV 2023] PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

[ICLR 2025] EdgeRunner: Auto-regressive Auto-encoder for Efficient Mesh Generation

Official implementation of Continuous 3D Perception Model with Persistent State

MambaGlue: Fast and Robust Local Feature Matching With Mamba @ ICRA'25

Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https://mv-dust3rp.github.io/

(AAAI2024) Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

A Transformer made of Rotation-equivariant Attention using Vector Neurons

[ICLR 2025] Point-SAM: Promptable 3D Segmentation Model for Point Clouds

[ECCV 2024] This repository represents the official implementation of PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration

[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration

Multiview Compressive Coding for 3D Reconstruction

Code for PointInfinity: Resolution-Invariant Point Diffusion Models

Official implementation of Occupancy-Based Dual Contouring (SIGGRAPH Asia 2024).

[ICML'24] Official Implementation for "3D Geometric Shape Assembly via Efficient Point Cloud Matching"

[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.

High-quality and editable surfel 3D Gaussian generation through native 3D diffusion (ICLR 2025)