MarkCrux
Follow
Stars
Official inference repo for FLUX.2 models
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
[CVPR 2025] RollingDepth: Video Depth without Video Models
[NeurIPS 2025 Spotlight] A Generalist Diffusion Model for Vision Perception
Wan: Open and Advanced Large-Scale Video Generative Models
DressRecon: Freeform 4D Human Reconstruction from Monocular Video (3DV'25 Oral)
Official repository for paper "MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement"
[CVPR2025] FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields
FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
This is a Qwen-Image ComfyUI plugin implementation that can run the full version with 24GB VRAM
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
[ICLR 2025] HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)
Official implementation of the paper "HRAvatar: High-Quality and Relightable Gaussian Head Avatar" [CVPR 2025]
Source code of the paper Scene-Aware 3D Multi-Human Motion Capture, EUROGRAPHICS 2023
GIGA: Generalizable Sparse Image-driven Gaussian Humans. 3DV 2026
[ICME 2025 Oral] Official implementation of "ABC-GS: Alignment-Based Controllable Style Transfer for 3D Gaussian Splatting"
Official inference repo for FLUX.1 models
计算机图形学 虎书 Fundamentals-Of-Computer-Graphics 第5版学习笔记（中文翻译）
OpenMMLab Pose Estimation Toolbox and Benchmark.
CARLA2Real is a tool that enhances the photorealism of the CARLA simulator in real-time, leveraging the Enhancing Photorealism Enhancement model proposed by Intel Labs.
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.