-
Nanyang Technological University
- Singapore
-
19:47
(UTC +08:00) - shangchenzhou.com
- @ShangchenZhou
Highlights
- Pro
Lists (13)
Sort Name ascending (A-Z)
Stars
Single Image to 3D using Cross-Domain Diffusion for 3D Generation
[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
State-of-the-art 2D and 3D Face Analysis Project
Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Open-MAGVIT2: Democratizing Autoregressive Visual Generation
Official implementation of Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
[NeurIPS 2024] Boosting the performance of consistency models with PCM!
Implementation of MagViT2 Tokenizer in Pytorch
Official Implementation of "Learning Inclusion Matching for Animation Paint Bucket Colorization"
[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.
Open-Sora: Democratizing Efficient Video Production for All
Transparent Image Layer Diffusion using Latent Transparency
Control Color: Multimodal Diffusion-based Interactive Image Colorization
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Official Code for Stable Cascade
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
[NeurIPS'23] Emergent Correspondence from Image Diffusion
[CVPR2024] VideoBooth: Diffusion-based Video Generation with Image Prompts
PyTorch codes for "Iterative Token Evaluation and Refinement for Real-World Super-Resolution", AAAI 2024
Official Implementation of paper "A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence"
Official PyTorch codes for "Enhancing Diffusion Models with Text-Encoder Reinforcement Learning", ECCV2024
[CVPR 2024] Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution
ModelScope: bring the notion of Model-as-a-Service to life.
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation