Learning Gradient Fields for Shape Generation

The collection of awesome papers on alignment of diffusion models.

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Blender add-on for editing scenes reconstructed with SuGaR or Gaussian Frosting.

[NeurIPS 2024] VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction

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

A Scalable Pipeline for Making Steerable Multi-Task Mid-Level Vision Datasets from 3D Scans [ICCV 2021]

[ICCV 2023] Official code for NeuS2

[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

[CVPR 2024] PIE-NeRF🍕: Physics-based Interactive Elastodynamics with NeRF

Codes and dataset for paper "IF-TONIR: Iteration-free Topology Optimization based on Implicit Neural Representations"

Web-based 3D visualization + Python

Coming soon

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

[NeurIPS 2023] Code for "Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives"

Pytorch Implementation of https://github.com/shubhtuls/volumetricPrimitives

Code release for "Learning Shape Abstractions by Assembling Volumetric Primitives " (CVPR 2017)

Code for CAPRI-Net

[ECCV 2024] SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction

[ECCV'24]Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering

[ICCV 2023] Code for "Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings"

持续维护的新浪微博采集工具🚀🚀🚀

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".

A curated list of resources for using LLMs to develop more competitive grant applications.

[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction