🚀 [ARXIV 2024] Pytorch implementation of 'Fast Feedforward 3D Gaussian Splatting Compression'

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

Code release for "3D reconstruction with fast dipole sums"

Octree-GS

[ECCV'24] On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy

[ECCV 2024 - ORAL] Official PyTorch implementation of Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

3D Reconstruction with Spatial Memory

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

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"

A 3DGS framework for omni urban scene reconstruction and simulation.

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

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

TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

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

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

Trim 3D Gaussian Splatting for Accurate Geometry Representation

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

GLOMAP - Global Structured-from-Motion Revisited

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Gaussian Splatting from VGGSfM and Mast3r, and their comparison

Official implementation of the SIGGRAPH 2024 paper "N-Dimensional Gaussians for Fitting of High Dimensional Functions"

[ECCV 2024] Official implementation of the paper "TAPTR: Tracking Any Point with Transformers as Detection"

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

[NeurIPS 2024] DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos