Stars
Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles
Official release for SplArt: Articulation Estimation and Part-level Reconstruction with 3D Gaussian Splatting.
[CVPR2025] Code Release for "FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting"
EditSplat: Multi-View Fusion & Attention-Guided Optimization for View-Consistent 3D Scene Editing (CVPR 2025) - Official Pytorch Code
A framework for easy application of established machine learning techniques on large, multi-dimensional images.
Course website for 6.S184/6.S975: Generative AI with Stochastic Differential Equations
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
Frequency-Space Neural Scene Representations for FMCW Radar
A Native Multimodal LLM for 3D Generation and Understanding
Official implementation of On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images. A. Meuleman, I. Shah, A. Lanvin, B. Kerbl, G. Drettakis, ACM TOG (proc. SIGGRAPH) 2025
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting (ICML 2025)
[IEEE RA-L 2025] Generate Weather with LLM. Code for "WeatherDG: LLM-assisted Procedural Weather Generation for Domain-Generalized Semantic Segmentation"
[ICRA 2024] Lightning NeRF: Efficient Hybrid Scene Representation for Autonomous Driving
Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)
Instant neural graphics primitives: lightning fast NeRF and more
Official implementation of "CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting"
ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS
Official implementation of EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
[Plug-and-Play] Generating Weather in any 3D Gaussian Scene
Implementation for Describe Anything: Detailed Localized Image and Video Captioning
[CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion