Stars
Implementation of Rotary Embeddings, from the Roformer paper, in Pytorch
Official implementation of Continuous 3D Perception Model with Persistent State
Official repository for "AM-RADIO: Reduce All Domains Into One"
A refactored codebase for Gaussian Splatting. Faster(3.5x)!! Modular!! Pure Python or CUDA Extension
[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
Ray tracing and hybrid rasterization of Gaussian particles
[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
Official implementation of TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
Differentiable Iso-Surface Extraction Package (DISO)
[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering
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".