Papers › Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation

Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation

9 Dec 2024arXiv:2412.06785archive 2025-07-28

Ruihan Gao, Kangle Deng, Gengshan Yang, Wenzhen Yuan, Jun-Yan Zhu

3D generation methods have shown visually compelling results powered by diffusion image priors. However, they often fail to produce realistic geometric details, resulting in overly smooth surfaces or geometric details inaccurately baked in albedo maps. To address this, we introduce a new method that incorporates touch as an additional modality to improve the geometric details of generated 3D assets. We design a lightweight 3D texture field to synthesize visual and tactile textures, guided by 2D diffusion model priors on both visual and tactile domains. We condition the visual texture generation on high-resolution tactile normals and guide the patch-based tactile texture refinement with a customized TextureDreambooth. We further present a multi-part generation pipeline that enables us to synthesize different textures across various regions. To our knowledge, we are the first to leverage high-resolution tactile sensing to enhance geometric details for 3D generation tasks. We evaluate our method in both text-to-3D and image-to-3D settings. Our experiments demonstrate that our method provides customized and realistic fine geometric textures while maintaining accurate alignment between two modalities of vision and touch.

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="2412.06785")

Code

Syntology Ran 1 of 18 code samples harvested from 1 repository linked to this paper; 17 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 18 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ruihangao/tactiledreamfusion officialmentioned in papermentioned 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

18 samples harvested; 1 ran; 1 honoured the contract we drafted; 17 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 · honoured contract
17unverified

Licence: 0 of the 18 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 ruihangao/tactiledreamfusion. “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.

b2mb ruihangao/tactiledreamfusion/TextureDreambooth/train_dreambooth.py official repository ran · honoured contract fingerprinted MIT (permissive) · 32380a050ca033d4 · report
convert ruihangao/tactiledreamfusion/cam_utils.py official repository unverified MIT (permissive) · 64f460074fb38474 · report
convert_normal2bae ruihangao/tactiledreamfusion/guidance/controlnet_utils.py official repository unverified MIT (permissive) · 5d93d2df27b15547 · report
cross ruihangao/tactiledreamfusion/utils.py official repository unverified MIT (permissive) · 659a59bc7fa9fc38 · report
dot ruihangao/tactiledreamfusion/utils.py official repository unverified MIT (permissive) · e35aafbf0069edb6 · report
find_patch_both ruihangao/tactiledreamfusion/data_preprocessing/image_quilting.py official repository unverified MIT (permissive) · 2db266fd695c4c54 · report
find_patch_horizontal ruihangao/tactiledreamfusion/data_preprocessing/image_quilting.py official repository unverified MIT (permissive) · 4ae22e3d4dc2849b · report
find_patch_vertical ruihangao/tactiledreamfusion/data_preprocessing/image_quilting.py official repository unverified MIT (permissive) · e24c674bc8afbdd5 · report
generate_gradients ruihangao/tactiledreamfusion/data_preprocessing/preprocess_tactile_data.py official repository unverified MIT (permissive) · 0e8fdb397f98e494 · report
heightmap_to_normal ruihangao/tactiledreamfusion/data_preprocessing/preprocess_tactile_data.py official repository unverified MIT (permissive) · 77f6a970e98bd175 · report
import_model_class_from_model_name_or_path ruihangao/tactiledreamfusion/TextureDreambooth/train_dreambooth.py official repository unverified MIT (permissive) · 2f00b39db5a81466 · report
length ruihangao/tactiledreamfusion/utils.py official repository unverified MIT (permissive) · 43cdc168f88caf9b · report
normal_to_image ruihangao/tactiledreamfusion/data_preprocessing/preprocess_tactile_data.py official repository unverified MIT (permissive) · 13ba5221922c0abc · report
parse_args ruihangao/tactiledreamfusion/TextureDreambooth/train_dreambooth.py official repository unverified MIT (permissive) · 7f93e189986fd065 · report
prep_unet ruihangao/tactiledreamfusion/guidance/cross_attention.py official repository unverified MIT (permissive) · ccda5c24afc0199e · report
scale_img_hwc ruihangao/tactiledreamfusion/mesh_renderer_tactile.py official repository unverified MIT (permissive) · 1eb01adb2d4db29c · report
scale_img_nhw ruihangao/tactiledreamfusion/mesh_renderer_tactile.py official repository unverified MIT (permissive) · 7d11ee5002c743ed · report
scale_img_nhwc ruihangao/tactiledreamfusion/mesh_renderer_tactile.py official repository unverified MIT (permissive) · e3e7b5863ff869ea · report

Tasks

3D GenerationImage to 3DText to 3DTexture Synthesis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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