Edit Banana: A framework for converting statistical formats into editable.

A paper list for Learning-based 3D Vision.

Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering

[NeurIPS 2025] Instant4D: 4D Gaussian Splatting in Minutes

Code Release for "Bilateral Guided Radiance Field Processing"

[NeurIPS 2025] Official code of Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

Sharp Monocular View Synthesis in Less Than a Second

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling

[ICCV 2025] The official implementation for DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction

Official implementation of BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting

VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning

[ICCV2025] PyTorch implementation of "Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models"

[NeurIPS 2025] Pixel-Perfect Depth

Official repository for our paper titled "UnDIVE: Generalized Underwater Video Enhancement Using Generative Priors"

This is the project for the paper of "Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition" in IJCAI2025

[CVPR'22 Oral] GMFlow: Learning Optical Flow via Global Matching

Official Pytorch Implementation for "VidToMe: Video Token Merging for Zero-Shot Video Editing" (CVPR 2024)

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

[ICCV 2025 Highlight] OminiControl: Minimal and Universal Control for Diffusion Transformer

[NeurIPS 2025] NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding

The first structured benchmark to evaluate and compare RSVLMs under a few-shot setting.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

Source code for 2021 ICCV paper "In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces"