Metal-native differentiable 3D Gaussian Splatting for Apple Silicon: fused forward+backward rasterizer on PyTorch MPS, no CUDA anywhere.
Source code for WACV 2026 paper "WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields"
3D Gaussian Splatting training on Apple Silicon. Metal kernels that numerically reproduce gsplat — no Python, no CUDA.
Turn a video into an explorable 3D Gaussian Splat — fully local on Apple Silicon
Real-time 3DGS studio for lenticular light-field displays.
AURA — Adaptive Unified Radiance Asset: the post-3DGS asset layer. Typed carriers (Gaussian/Beta), calibrated + certified per-carrier confidence exported in KHR_gaussian_splatting & OpenUSD 26.03, unified ray-query, relight preview.
RadianceKit — native macOS app for 3D Gaussian Splatting (local, Apple Silicon/Metal). Open docs: export-format reference, capture guide & FAQ.
Capture reality with your phone, explore it as a real-time photorealistic 3D scene — browser-based Gaussian Splatting viewer. WebGL performance engineering, fully client-side.
Native Android Gaussian splatting SDK: Vulkan GPU visibility, radix sorting, hierarchical LOD, SH and walk/fly navigation. Experimental alpha.
DisplayXR demo — real-time 3D Gaussian Splatting viewer for glasses-free 3D displays (OpenXR + Vulkan, Windows & macOS).
2,751 geotagged aerial images (45.0 GB) of Grant Park & downtown Chicago, empty in June 2020. Winner, RealityCapture #RCmonthlyChallenge Aug 2020. CC BY 4.0.
Few-shot 3D Gaussian Splatting for sparse-view (DTU) reconstruction, using an RGBD patch-diffusion prior (DiffusioNeRF) and PatchmatchNet MVS initialization.
Open-vocabulary 3D instance segmentation on Radiant Foam - OpenSplat3D's recipe distilled into Voronoi cells
Turning a handheld phone video into a 3D Gaussian splat of a real room: three capture runs, the measurements that explain the difference, and the two-line fix that took COLMAP from 2/353 to 351/353 registered images.
Denoising-diffusion RGBD patch prior for regularizing radiance fields — fork of nianticlabs/diffusionerf, used as the diffusion regularizer for few-shot 3DGS.
Drop-in, idempotent speed patches for PGSR surface-reconstruction training — removes per-iteration PCIe transfers, redundant ones-kernel convolutions, and GPU-CPU logging syncs (plus a real EMA-logging bug) with CPU-proven numerical parity: same geometry, lower GPU bill.
Differentiable Gaussian rasterization with depth & alpha output — fork of graphdeco-inria/diff-gaussian-rasterization, used for few-shot 3DGS.
812 geotagged images (15.1 GB) of one tree, ground to canopy. Winner, RealityCapture #RCmonthlyChallenge Aug 2020. CC BY 4.0.
React Native component for real-time Gaussian splatting: load an SPZ scene, pick a quality preset, and walk through it from JavaScript.
Photos to 3D on a free Colab GPU: CUDA-enabled COLMAP matching, a desktop app for camera positions, and Gaussian Splatting training. 320 photos matched in 28 minutes instead of 11 hours.
To associate your repository with the radiance-fields topic, visit your repo's landing page and select "manage topics."