Papers › TextDeformer: Geometry Manipulation using Text Guidance

TextDeformer: Geometry Manipulation using Text Guidance

26 Apr 2023arXiv:2304.13348archive 2025-07-28

William Gao, Noam Aigerman, Thibault Groueix, Vladimir G. Kim, Rana Hanocka

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2304.13348")

Code

Syntology Ran 3 of 16 code samples harvested from 1 repository linked to this paper; 13 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

threedle/TextDeformer officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 3 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
2ran
13unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from threedle/TextDeformer. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

dot threedle/TextDeformer/nvdiffmodeling/src/util.py official repository ran fingerprinted MIT (permissive) · 072f2ec9852bb19f · report
length threedle/TextDeformer/nvdiffmodeling/src/util.py official repository ran fingerprinted MIT (permissive) · de6b9750cabc6a63 · report
shade threedle/TextDeformer/nvdiffmodeling/src/render.py official repository ran · fixture could not drive it MIT (permissive) · e5155d851cbebb5a · report
aabb threedle/TextDeformer/nvdiffmodeling/src/mesh.py official repository unverified MIT (permissive) · 71588ea43749ba8a · report
avg_edge_length threedle/TextDeformer/nvdiffmodeling/src/regularizer.py official repository unverified MIT (permissive) · 997e97bfa3b50b09 · report
center_by_reference threedle/TextDeformer/nvdiffmodeling/src/mesh.py official repository unverified MIT (permissive) · b8b5019045a6e3ce · report
cosine_sample threedle/TextDeformer/utilities/camera.py official repository unverified MIT (permissive) · 46b27476b8041014 · report
edge_length_regularizer threedle/TextDeformer/nvdiffmodeling/src/regularizer.py official repository unverified MIT (permissive) · 9d1d964d8e4e5e48 · report
get_random_bg threedle/TextDeformer/utilities/camera.py official repository unverified MIT (permissive) · 74ff9251845fb16e · report
laplace_regularizer_const threedle/TextDeformer/nvdiffmodeling/src/regularizer.py official repository unverified MIT (permissive) · 31e09d3a07b8180c · report
load_mtl threedle/TextDeformer/nvdiffmodeling/src/material.py official repository unverified MIT (permissive) · 36562037e3dea340 · report
load_obj threedle/TextDeformer/nvdiffmodeling/src/obj.py official repository unverified MIT (permissive) · 9932280d3974e132 · report
merge_materials threedle/TextDeformer/nvdiffmodeling/src/material.py official repository unverified MIT (permissive) · 70b072c635219a5c · report
persp_proj threedle/TextDeformer/utilities/camera.py official repository unverified MIT (permissive) · b5152d98492bb987 · report
reflect threedle/TextDeformer/nvdiffmodeling/src/util.py official repository unverified MIT (permissive) · f8332e15b46ba812 · report
unit_size threedle/TextDeformer/nvdiffmodeling/src/mesh.py official repository unverified MIT (permissive) · b545da6137bd6930 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionCLIPDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionOPTResidual ConnectionSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections