WildGaussians: 3D Gaussian Splatting In the Wild

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

Original implementation of "FLoD: Integrating Flexible Level of Detail into 3D Gaussian Splatting for Customizable Rendering"

[ECCV 2024] Official repository for "Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting"

Dynamic 2D Gaussians: Geometrically accurate radiance fields for dynamic objects

Official implementation for the SIGGRAPH Asia 2024 paper SPARK: Self-supervised Personalized Real-time Monocular Face Capture

Repo for the paper "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023)

video splat

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

3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt.

3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

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

(SIGGRAPH Asia 2024) This is the official PyTorch implementation of SIGGRAPH Asia 2024 paper: DrawingSpinUp: 3D Animation from Single Character Drawings

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

Out-of-core watertight surface reconstruction from LiDAR point cloud

Official implementation of the paper "DeepMIF: Deep Monotonic Implicit Fields for Large-Scale LiDAR 3D Mapping"

FedSurfGS: Scalable 3D Surface Gaussian Splatting with Federated Learning for Large Scene Reconstruction

GigaGS: Scaling up Planar-Based 3D Gaussians for Large Scene Surface Reconstruction

LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian(Published in SIGGRAPH Asia 2024)

StableDelight: Revealing Hidden Textures by Removing Specular Reflections

[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

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

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Dead simple FLUX LoRA training UI with LOW VRAM support

[ECCV 2024] Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction

Casual for fun implementation of autograd in numpy, train an MLP in MNIST, for learning/teaching purposes