An efficient and research-friendly Gaussian Splatting framework based on “Faster-GS: Analyzing and Improving Gaussian Splatting Optimization”

[ICCV 2025] LightSwitch: Multi-view Relighting with Material-guided Diffusion

Non-Aligned Reference Image Quality Assessment for Novel View Synthesis

Official PyTorch implementation for "Learning to See in the Extremely Dark"

Information-Driven Design of Imaging Systems

Unified framework for robot learning built on NVIDIA Isaac Sim

Convolutional PyTorch debayering / demosaicing layers

Minimalist Vision with Freeform Pixels (ECCV 24)

Colour Science for Python

(CVPR 2025 Highlight) Official repository of paper "AODRaw: Towards RAW Object Detection in Diverse Conditions" (https://arxiv.org/pdf/2411.15678)

IBGS: Image-Based Gaussian Splatting (NeurIPS2025)

Sharp Monocular View Synthesis in Less Than a Second

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…

(CVPR 2025 Highlight) Official repository of paper "AODRaw: Towards RAW Object Detection in Diverse Conditions" (https://arxiv.org/pdf/2411.15678)

Official PyTorch implementation of "Perception-Inspired Color Space Design for Photo White Balance Editing" (WACV 2026).

Code for the paper: "Modular Neural Image Signal Processing". A modular neural ISP with interpretable stages, multi-style rendering, cross-camera generalization, and post-editable re-rendering with…

Reference code for the paper: "Raw-JPEG Adapter: Efficient Raw Image Compression with JPEG." Learnable, invertible raw-to-JPEG pre-processing with parameters stored in the JPEG COM (<64 KB), enabli…

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

[AAAI 2026] SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements

Official implementation of SIGGRAPH 2025 paper "Image-GS: Content-Adaptive Image Representation via 2D Gaussians"

Code for paper: Examining Joint Demosaicing and Denoising for Single-, Quad- and Nona-Bayer Patterns

[ICLR 2025] RGB-Event ISP: The Dataset and Benchmark

Depth Anything 3

[NeurIPS 2025] I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Code for projects on inverse rendering via radiance caching, at ECCV 2024 and CVPR 2025