Code release for IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images (CVPR 2025)

GLUEMAP: Global Structure-from-Motion Meets Feedforward Reconstruction

Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction

Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction

Official release of the Eyeful Tower dataset, a high-fidelity multi-view capture of 11 real-world scenes, from the paper “VR-NeRF High-Fidelity Virtualized Walkable Spaces” (Xu et al., SIGGRAPH Asi…

official implementation of paper MegaNorm: Local Patch Embeddings for Efficient and Robust Point Normal Orientation at Super-Large Scale

Persistent/Immutable/Functional data structures for Python

[CVPR 2025] MINIMA: Modality Invariant Image Matching

Solving partial differential equations in participating media.

[CVPR 2026] UniCorrn: Unified Correspondence Transformer Across 2D and 3D

GLUEMAP: Global Structure-from-Motion Meets Feedforward Reconstruction

Adding realistic film grain to pictures

PDAL is Point Data Abstraction Library. GDAL for point cloud data.

Sparse nonlinear least squares in JAX

FIPT: Factorized Inverse Path Tracing

Fit compact primitive assemblies (SuperFrusta, cuboids, superquadrics) to 3D shapes via residual fitting. CVPR 2026.

Simple 3D Packing

Interactive Point Cloud Segmentation (3DV 2026 Best Paper Candidate)

Packing irregular objects with deep reinforcement learning.

[CVPR 2026] FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning

easy to use retry decorator in python

Simple 3D Packing

Fuse multiple depth frames into a TSDF voxel volume.

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

3D reconstruction system to creating detailed scene geometry from range video.

[Siggraph 2017] BundleFusion: Real-time Globally Consistent 3D Reconstruction using Online Surface Re-integration

Ray tracing and hybrid rasterization of Gaussian particles

[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

Simple, Pythonic remote execution and deployment.