MegaFlow: Zero-Shot Large Displacement Optical Flow

[CVPR 2026] Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation

An efficient and research-friendly Gaussian Splatting framework described in the CVPR'26 paper "Faster-GS: Analyzing and Improving Gaussian Splatting Optimization"

[NeurIPS 2025] DisMo: DIsentangled Motion Representations for Open-World Motion Transfer

single 3D shape diffusion model

[ICLR 2026] Adapting Self-Supervised Representations as a Latent Space for Efficient Generation

[ICCV 2025] Stochastic Interpolants for Revealing Stylistic Flows across the History of Art

[ECCV 2024] CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians

source code for the ECCV18 paper A Style-Aware Content Loss for Real-time HD Style Transfer

The official implementation of "[MASK] is All You Need"

[AAAI 2025] Does VLM Classification Benefit from LLM Description Semantics?

[SIGGRAPH Asia 2025] PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion

[CVPR 2025] RollingDepth: Video Depth without Video Models

[ICCV 2025] SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models

Implementation of normalizing flows from 1d to Nd

[CVPR 2026] A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"

[CVPR 2025] Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

Official implementation of 3Doodle: Compact Abstraction of Objects with 3D Strokes (SIGGRAPH 24', Journal track)

A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)

[AAAI 2025] Event-Enhanced Blurry Video Super-Resolution

High-Resolution Image Synthesis with Latent Diffusion Models

A latent text-to-image diffusion model