mlsanityData to 7 Oct 2026

TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimization

arXiv 2607.14927 ↗First posted 16 Jul 2026cs.CVcited by 2

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

While recent flow-matching 3D generative models (e.g., VecSet) adopt structured representations, their tokens share global context, causing conventional training-free editing to suffer from semantic artifacts such as collapsed preserved regions or incomplete transformations. To address this, we propose TanGO, a training-free framework that enables adaptive per-token steering in the tangent space of generative dynamics. To realize this selective control, we formulate a one-step optimal control rule and determine the strength of each token's control signal using a von Mises-Fisher inspired directional discrepancy derived from the source and target velocity fields. Experiments show that TanGO substantially reduces structural artifacts and achieves state-of-the-art performance, outperforming existing 3D editing baselines. The code is publicly available at https://github.com/siw00-lim/TanGO.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 35 of its 36 references that are in the map. First posted on arXiv 16 Jul 2026.

Builds on

35 of 36 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models10 Feb
  2. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders23 Dec
  3. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  4. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer23 May
  5. 2024Generic 3D Diffusion Adapter Using Controlled Multi-View Editing18 Mar
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  7. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  8. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  9. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  10. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  4. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  5. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  7. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  8. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  9. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  10. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
  11. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 332
  12. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
13 more
  1. 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
  2. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 214
  3. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
  4. 2024MV-Adapter: Multi-view Consistent Image Generation Made Easycited by 111
  5. 2023TextDeformer: Geometry Manipulation using Text Guidancecited by 94
  6. 2024Instant3dit: Multiview Inpainting for Fast Editing of 3D Objectscited by 43
  7. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scalecited by 41
  8. 2025VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Spacecited by 40
  9. 2024FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editingcited by 31
  10. 2025NANO3D: A Training-Free Approach for Efficient 3D Editing Without Maskscited by 29
  11. 2025EditP23: 3D Editing via Propagation of Image Prompts to Multi-Viewcited by 19
  12. 2024DNI: Dilutional Noise Initialization for Diffusion Video Editingcited by 12
  13. 2025AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flowscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editingcited by 0
  2. 2026Scaling Versatile 3D Assets Editing with a Million-Scale Datasetcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning 3D Editing without Paired Supervision via Generative Prior Distillation
  2. 2026ShapeUP: Scalable Image-Conditioned 3D Editing
  3. 2026EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation
  4. 20253D-LATTE: Latent Space 3D Editing from Textual Instructions
  5. 2025Feedforward 3D Editing via Text-Steerable Image-to-3D
  6. 2026SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing
  7. 2026FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition
  8. 2026UniMoFlow: Grounding Instruction-Driven 3D Human Motion Editing in Generation