{"id":51310748,"url":"https://github.com/alessiopittiglio/dl-project","last_synced_at":"2026-07-01T03:34:31.748Z","repository":{"id":326029828,"uuid":"997342897","full_name":"alessiopittiglio/dl-project","owner":"alessiopittiglio","description":"A TensorFlow implementation of Neural Radiance Fields (NeRF) for synthesizing novel views of complex 3D scenes from a sparse set of 2D images.","archived":false,"fork":false,"pushed_at":"2025-11-25T02:40:21.000Z","size":6690,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-07-01T03:34:30.725Z","etag":null,"topics":["computer-vision","nerf","novel-view-synthesis","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/alessiopittiglio.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-06-06T11:15:17.000Z","updated_at":"2025-11-25T02:40:24.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/alessiopittiglio/dl-project","commit_stats":null,"previous_names":["alessiopittiglio/dl-project"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/alessiopittiglio/dl-project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiopittiglio%2Fdl-project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiopittiglio%2Fdl-project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiopittiglio%2Fdl-project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiopittiglio%2Fdl-project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alessiopittiglio","download_url":"https://codeload.github.com/alessiopittiglio/dl-project/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alessiopittiglio%2Fdl-project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34992071,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-01T02:00:05.325Z","response_time":130,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["computer-vision","nerf","novel-view-synthesis","tensorflow"],"created_at":"2026-07-01T03:34:31.138Z","updated_at":"2026-07-01T03:34:31.730Z","avatar_url":"https://github.com/alessiopittiglio.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Novel View Synthesis with NeRF\n\n## Project Overview\n\nThe goal of this project is to develop a model for Novel View Synthesis. This involves generating new images of a 3D object from viewpoints that are not present in the initial set of images. The model is trained on RGB images and their corresponding camera poses.\n\n## Dataset\nThe project uses the NeRF Synthetic Dataset provided by Cornell University, specifically the Lego scene.\n\nDataset structure:\n\n```\nnerf_synthetic/\n└── SCENE_NAME/\n    ├── train/\n    ├── val/\n    ├── test/\n    ├── transforms_train.json\n    ├── transforms_val.json\n    └── transforms_test.json\n```\n\n## Technical Approach\nThe solution implements the NeRF paper from scratch. The model is Multi-Layer Perceptron (MLP). It takes the encoded position and viewing direction as input and predicts the RGB color and volume density ($\\sigma$) at that point. The architecture is composed of 8 fully connected layers with a skip connection at the 4th layer.\n\n## Training\nA two-phase strategy was adopted: an initial phase of 50,000 iterations followed by a fine-tuning phase of 10,000 iterations. The model achieved a final PSNR of 30.3 on the test set.\n\n## 360° View Synthesis\n\nA 360° camera rotation generated by the trained NeRF model is shown below.\n\n![NeRF Rotation](assets/rotation.gif)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falessiopittiglio%2Fdl-project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falessiopittiglio%2Fdl-project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falessiopittiglio%2Fdl-project/lists"}