{"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/hifa-high-fidelity-text-to-3d-with-advanced","title":"HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance","arxiv_id":"2305.18766","date":"2023-05-30","proceeding":null,"authors":["Junzhe Zhu","Peiye Zhuang","Sanmi Koyejo"],"abstract":"The advancements in automatic text-to-3D generation have been remarkable. Most existing methods use pre-trained text-to-image diffusion models to optimize 3D representations like Neural Radiance Fields (NeRFs) via latent-space denoising score matching. Yet, these methods often result in artifacts and inconsistencies across different views due to their suboptimal optimization approaches and limited understanding of 3D geometry. Moreover, the inherent constraints of NeRFs in rendering crisp geometry and stable textures usually lead to a two-stage optimization to attain high-resolution details. This work proposes holistic sampling and smoothing approaches to achieve high-quality text-to-3D generation, all in a single-stage optimization. We compute denoising scores in the text-to-image diffusion model's latent and image spaces. Instead of randomly sampling timesteps (also referred to as noise levels in denoising score matching), we introduce a novel timestep annealing approach that progressively reduces the sampled timestep throughout optimization. To generate high-quality renderings in a single-stage optimization, we propose regularization for the variance of z-coordinates along NeRF rays. To address texture flickering issues in NeRFs, we introduce a kernel smoothing technique that refines importance sampling weights coarse-to-fine, ensuring accurate and thorough sampling in high-density regions. Extensive experiments demonstrate the superiority of our method over previous approaches, enabling the generation of highly detailed and view-consistent 3D assets through a single-stage training process.","url_abs":"https://arxiv.org/abs/2305.18766v4","url_pdf":"https://arxiv.org/pdf/2305.18766v4.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":"hifa-high-fidelity-text-to-3d-with-advanced","repo_url":"https://github.com/JunzheJosephZhu/HiFA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"text-to-3d","task_name":"Text to 3D"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.18766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18766"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JunzheJosephZhu/HiFA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c999c85b86b93312","entry":"numpy_to_torch","repo":"JunzheJosephZhu/HiFA","repo_kind":"official","path":"metric_utils.py","file_url":"https://github.com/JunzheJosephZhu/HiFA/blob/HEAD/metric_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c999c85b86b93312"}},{"code_sha256_prefix":"fc359761682b9f87","entry":"bsdf_frostbite","repo":"JunzheJosephZhu/HiFA","repo_kind":"official","path":"nerf/bsdf.py","file_url":"https://github.com/JunzheJosephZhu/HiFA/blob/HEAD/nerf/bsdf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc359761682b9f87"}},{"code_sha256_prefix":"20945f6ad60e0aea","entry":"bsdf_lambert","repo":"JunzheJosephZhu/HiFA","repo_kind":"official","path":"nerf/bsdf.py","file_url":"https://github.com/JunzheJosephZhu/HiFA/blob/HEAD/nerf/bsdf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20945f6ad60e0aea"}},{"code_sha256_prefix":"6e1b8b0343ac0d43","entry":"bsdf_prepare_shading_normal","repo":"JunzheJosephZhu/HiFA","repo_kind":"official","path":"nerf/bsdf.py","file_url":"https://github.com/JunzheJosephZhu/HiFA/blob/HEAD/nerf/bsdf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e1b8b0343ac0d43"}},{"code_sha256_prefix":"925971c108f1976f","entry":"get_encoder","repo":"JunzheJosephZhu/HiFA","repo_kind":"official","path":"encoding.py","file_url":"https://github.com/JunzheJosephZhu/HiFA/blob/HEAD/encoding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"925971c108f1976f"}},{"code_sha256_prefix":"b7f0e912438abda8","entry":"poisson_mesh_reconstruction","repo":"JunzheJosephZhu/HiFA","repo_kind":"official","path":"meshutils.py","file_url":"https://github.com/JunzheJosephZhu/HiFA/blob/HEAD/meshutils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b7f0e912438abda8"}},{"code_sha256_prefix":"1b69fc463a92e2d5","entry":"score_from_method_for_dataset","repo":"JunzheJosephZhu/HiFA","repo_kind":"official","path":"metric_utils.py","file_url":"https://github.com/JunzheJosephZhu/HiFA/blob/HEAD/metric_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b69fc463a92e2d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}