{"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/textdeformer-geometry-manipulation-using-text","title":"TextDeformer: Geometry Manipulation using Text Guidance","arxiv_id":"2304.13348","date":"2023-04-26","proceeding":null,"authors":["William Gao","Noam Aigerman","Thibault Groueix","Vladimir G. Kim","Rana Hanocka"],"abstract":"We present a technique for automatically producing a deformation of an input triangle mesh, guided solely by a text prompt. Our framework is capable of deformations that produce both large, low-frequency shape changes, and small high-frequency details. Our framework relies on differentiable rendering to connect geometry to powerful pre-trained image encoders, such as CLIP and DINO. Notably, updating mesh geometry by taking gradient steps through differentiable rendering is notoriously challenging, commonly resulting in deformed meshes with significant artifacts. These difficulties are amplified by noisy and inconsistent gradients from CLIP. To overcome this limitation, we opt to represent our mesh deformation through Jacobians, which updates deformations in a global, smooth manner (rather than locally-sub-optimal steps). Our key observation is that Jacobians are a representation that favors smoother, large deformations, leading to a global relation between vertices and pixels, and avoiding localized noisy gradients. Additionally, to ensure the resulting shape is coherent from all 3D viewpoints, we encourage the deep features computed on the 2D encoding of the rendering to be consistent for a given vertex from all viewpoints. We demonstrate that our method is capable of smoothly-deforming a wide variety of source mesh and target text prompts, achieving both large modifications to, e.g., body proportions of animals, as well as adding fine semantic details, such as shoe laces on an army boot and fine details of a face.","url_abs":"https://arxiv.org/abs/2304.13348v1","url_pdf":"https://arxiv.org/pdf/2304.13348v1.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":"textdeformer-geometry-manipulation-using-text","repo_url":"https://github.com/threedle/TextDeformer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"opt","method_name":"OPT"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.13348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.13348"}},"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/threedle/TextDeformer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_fixture":1,"unverified":13},"by_repo_kind":{"official":{"samples":16,"ran":3,"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":"072f2ec9852bb19f","entry":"dot","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/util.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/util.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"072f2ec9852bb19f"}},{"code_sha256_prefix":"de6b9750cabc6a63","entry":"length","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/util.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/util.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"de6b9750cabc6a63"}},{"code_sha256_prefix":"e5155d851cbebb5a","entry":"shade","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/render.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/render.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5155d851cbebb5a"}},{"code_sha256_prefix":"71588ea43749ba8a","entry":"aabb","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/mesh.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/mesh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71588ea43749ba8a"}},{"code_sha256_prefix":"997e97bfa3b50b09","entry":"avg_edge_length","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/regularizer.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/regularizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"997e97bfa3b50b09"}},{"code_sha256_prefix":"b8b5019045a6e3ce","entry":"center_by_reference","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/mesh.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/mesh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8b5019045a6e3ce"}},{"code_sha256_prefix":"46b27476b8041014","entry":"cosine_sample","repo":"threedle/TextDeformer","repo_kind":"official","path":"utilities/camera.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/utilities/camera.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46b27476b8041014"}},{"code_sha256_prefix":"9d1d964d8e4e5e48","entry":"edge_length_regularizer","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/regularizer.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/regularizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d1d964d8e4e5e48"}},{"code_sha256_prefix":"74ff9251845fb16e","entry":"get_random_bg","repo":"threedle/TextDeformer","repo_kind":"official","path":"utilities/camera.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/utilities/camera.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74ff9251845fb16e"}},{"code_sha256_prefix":"31e09d3a07b8180c","entry":"laplace_regularizer_const","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/regularizer.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/regularizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31e09d3a07b8180c"}},{"code_sha256_prefix":"36562037e3dea340","entry":"load_mtl","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/material.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/material.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36562037e3dea340"}},{"code_sha256_prefix":"9932280d3974e132","entry":"load_obj","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/obj.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/obj.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9932280d3974e132"}},{"code_sha256_prefix":"70b072c635219a5c","entry":"merge_materials","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/material.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/material.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70b072c635219a5c"}},{"code_sha256_prefix":"b5152d98492bb987","entry":"persp_proj","repo":"threedle/TextDeformer","repo_kind":"official","path":"utilities/camera.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/utilities/camera.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5152d98492bb987"}},{"code_sha256_prefix":"f8332e15b46ba812","entry":"reflect","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/util.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f8332e15b46ba812"}},{"code_sha256_prefix":"b545da6137bd6930","entry":"unit_size","repo":"threedle/TextDeformer","repo_kind":"official","path":"nvdiffmodeling/src/mesh.py","file_url":"https://github.com/threedle/TextDeformer/blob/HEAD/nvdiffmodeling/src/mesh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b545da6137bd6930"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}