Stars
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
[PAMI 2022, CVPR 2023] ASH: Parallel Spatial Hashing for Fast Scene Reconstruction
Original Pytorch implementation of the GPDM model introduced in "Generating natural images with direct patch distributions matching"
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
20x Real-time superpixel SLIC Implementation with CPU
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
GPU programming related news and material links
Code for the paper "pix2gestalt: Amodal Segmentation by Synthesizing Wholes" (CVPR 2024)
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Official Repository of the Stanford-ORB dataset
Unbiased Physically Based Differentiable Renderer
CUDA accelerated rasterization of gaussian splatting
[ICCV 2023] Pytorch implementation of "S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields".
Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation (CVPR 2023)
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
[ICCV2023] GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction
Easy NeRF synthetic dataset creation within Blender
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
Gin provides a lightweight configuration framework for Python
Typer, build great CLIs. Easy to code. Based on Python type hints.
Code release for 360monodepth. With our framework we achieve monocular depth estimation for high resolution 360° images based on aligning and blending perspective depth maps.
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs