{"id":20161903,"url":"https://github.com/ailab-cvc/hifi-123","last_synced_at":"2025-08-20T10:32:28.342Z","repository":{"id":199670756,"uuid":"703440871","full_name":"AILab-CVC/HiFi-123","owner":"AILab-CVC","description":"[ECCV 2024] HiFi-123: Towards High-fidelity One Image to 3D Content Generation","archived":false,"fork":false,"pushed_at":"2024-07-12T09:42:35.000Z","size":8628,"stargazers_count":59,"open_issues_count":0,"forks_count":0,"subscribers_count":12,"default_branch":"main","last_synced_at":"2024-12-07T14:35:16.103Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://drexubery.github.io/HiFi-123/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AILab-CVC.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-11T08:50:55.000Z","updated_at":"2024-10-22T12:34:16.000Z","dependencies_parsed_at":"2024-11-14T03:00:40.119Z","dependency_job_id":null,"html_url":"https://github.com/AILab-CVC/HiFi-123","commit_stats":null,"previous_names":["ailab-cvc/hifi-123"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AILab-CVC%2FHiFi-123","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AILab-CVC%2FHiFi-123/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AILab-CVC%2FHiFi-123/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AILab-CVC%2FHiFi-123/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AILab-CVC","download_url":"https://codeload.github.com/AILab-CVC/HiFi-123/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":230415318,"owners_count":18222158,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-14T00:21:41.079Z","updated_at":"2024-12-19T10:09:55.529Z","avatar_url":"https://github.com/AILab-CVC.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HiFi-123: Towards High-fidelity One Image to 3D Content Generation\n\u003cdiv align=\"center\"\u003e\n \u003ca href='https://arxiv.org/abs/2310.06744'\u003e\u003cimg src='https://img.shields.io/badge/arXiv-2310.06744-b31b1b.svg'\u003e\u003c/a\u003e \u0026nbsp;\n \u003ca href='https://drexubery.github.io/HiFi-123/'\u003e\u003cimg src='https://img.shields.io/badge/Project-Page-Green'\u003e\u003c/a\u003e \u0026nbsp;\n\n\u003cstrong\u003eECCV 2024\u003c/strong\u003e\n\u003c/div\u003e\n\n## 📝 Changelog\n- __[2024.7.12]__: Release the code for reference-guided novel view enhancement (RGNV), we will soon add Zero-1-to-3 support for the RGNV pipeline and release the code for Image-to-3D generation.\n\u003cbr\u003e\n\n## 🔆 Introduction\nOfficial implementation of HiFi-123: Towards High-fidelity One Image to 3D Content Generation, we are working hard on cleaning the code, please stay tuned.\n\n## ⚙️ Setup for Reference-guided novel view enhancement (RGNV)\n### Install Environment via Anaconda (Recommended)\n```bash\ncd ./HiFi-NVS\nconda create -n rgnv python=3.9.7\nconda activate rgnv\n\npip install -r requirements_rgnv.txt\n```\nNote that the diffusers version should be exactly the same with our requirements.\n\n## 💫 Inference for Reference-guided novel view enhancement (RGNV)\n### 1. Command line\n1) Download the pre-trained depth estimation and matting model from [here](https://drive.google.com/file/d/1LEOmXAeylde0DSvUmfKeEt9_H1ENcdwD/view?usp=sharing), and put them in `./ptms`.\n2) Download pretrained stable-diffusion-2-depth model via [Hugging Face](https://huggingface.co/stabilityai/stable-diffusion-2-depth).\n2) Download pretrained stable-diffusion-x4-upscaler model via [Hugging Face](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler).\n3) Input the following commands in terminal, you can upload your source image (the high-quality reference image) and coarse image (the generated coarse novel view) then specify their path in the script. We use a specified background `./load/bg2.png` during processing, since the stable-diffusion-2-depth model is sensitive to pure background.\n```bash\n  sh run.sh\n```\n\n## ⚙️ Setup for Image-to-3D generation\nOur code will be integrated into threestudio to combine with a variety of models implemented by threestudio, making our method a generalized tool for enhancing texture quality in Image-to-3D generation.\n\n## 🤗 Acknowledgements\nMany thanks to the projects [threestudio](https://github.com/threestudio-project/threestudio), [MasaCtrl](https://github.com/TencentARC/MasaCtrl).\n\n## 🤝 Citation\n```bib\n  @article{yu2023hifi,\n      title={Hifi-123: Towards high-fidelity one image to 3d content generation},\n      author={Yu, Wangbo and Yuan, Li and Cao, Yan-Pei and Gao, Xiangjun and Li, Xiaoyu \n          and Hu, Wenbo and Quan, Long and Shan, Ying and Tian, Yonghong},\n      journal={arXiv preprint arXiv:2310.06744},\n      year={2023}\n      }\n  }\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Failab-cvc%2Fhifi-123","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Failab-cvc%2Fhifi-123","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Failab-cvc%2Fhifi-123/lists"}