{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/nerflix-high-quality-neural-view-synthesis-by","title":"NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer","arxiv_id":"2303.06919","date":"2023-03-13","proceeding":"CVPR 2023 1","authors":["Kun Zhou","Wenbo Li","Yi Wang","Tao Hu","Nianjuan Jiang","Xiaoguang Han","Jiangbo Lu"],"abstract":"Neural radiance fields (NeRF) show great success in novel view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation inaccuracy. Even with high-quality training frames, the synthetic novel views produced by NeRF models still suffer from notable rendering artifacts, such as noise, blur, etc. Towards to improve the synthesis quality of NeRF-based approaches, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer. Specially, we design a NeRF-style degradation modeling approach and construct large-scale training data, enabling the possibility of effectively removing NeRF-native rendering artifacts for existing deep neural networks. Moreover, beyond the degradation removal, we propose an inter-viewpoint aggregation framework that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.","url_abs":"https://arxiv.org/abs/2303.06919v2","url_pdf":"https://arxiv.org/pdf/2303.06919v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"nerflix-high-quality-neural-view-synthesis-by","repo_url":"https://github.com/redrock303/NeRFLiX_CPVR2023","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"neural-rendering","task_name":"Neural Rendering"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/novel-view-synthesis-on-llff","task":"Novel View Synthesis","dataset":"LLFF","model":"TensoRF + NeRFLiX","rank_in_archive_order":1,"of":15,"metrics":{"LPIPS":"0.149","PSNR":"27.39","SSIM":"0.867"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-llff","task":"Novel View Synthesis","dataset":"LLFF","model":"Plenoxels + NeRFLiX","rank_in_archive_order":4,"of":15,"metrics":{"LPIPS":"0.156","PSNR":"26.9","SSIM":"0.864"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-tanks-and-temples","task":"Novel View Synthesis","dataset":"Tanks and Temples","model":"TensoRF + NeRFLiX","rank_in_archive_order":2,"of":10,"metrics":{"PSNR":"28.94","SSIM":"0.93"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-tanks-and-temples","task":"Novel View Synthesis","dataset":"Tanks and Temples","model":"Plenoxels + NeRFLiX","rank_in_archive_order":3,"of":10,"metrics":{"PSNR":"28.61"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-tanks-and-temples","task":"Novel View Synthesis","dataset":"Tanks and Temples","model":"DIVeR + NeRFLiX","rank_in_archive_order":10,"of":10,"metrics":{"SSIM":"0.924"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.06919","atlas_url":"https://app.syntology.ai/?focus=2303.06919","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}