TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulation
Not on the map. Why?
Abstract (arXiv)
Despite significant strides in the field of 3D scene editing, current methods encounter substantial challenge, particularly in preserving 3D consistency in multi-view editing process. To tackle this challenge, we propose a progressive 3D editing strategy that ensures multi-view consistency via a Trajectory-Anchored Scheme (TAS) with a dual-branch editing mechanism. Specifically, TAS facilitates a tightly coupled iterative process between 2D view editing and 3D updating, preventing error accumulation yielded from text-to-image process. Additionally, we explore the relationship between optimization-based methods and reconstruction-based methods, offering a unified perspective for selecting superior design choice, supporting the rationale behind the designed TAS. We further present a tuning-free View-Consistent Attention Control (VCAC) module that leverages cross-view semantic and geometric reference from the source branch to yield aligned views from the target branch during the editing of 2D views. To validate the effectiveness of our method, we analyze 2D examples to demonstrate the improved consistency with the VCAC module. Further extensive quantitative and qualitative results in text-guided 3D scene editing indicate that our method achieves superior editing quality compared to state-of-the-art methods. We will make the complete codebase publicly available following the conclusion of the review process.
Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 48 of its 53 references that are in the map. First posted on arXiv 2 Jul 2024.
Builds on
48 of 53 references.
References · 48
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
- 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
- 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
- 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
- 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
- 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
- 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
36 more
- 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
- 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
- 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 387
- 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
- 2023LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matchingcited by 290
- 2022Diffusion models as plug-and-play priorscited by 230
- 2024A Survey on 3D Gaussian Splattingcited by 221
- 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
- 2023DreamEditor: Text-Driven 3D Scene Editing with Neural Fieldscited by 154
- 2024Recent Advances in 3D Gaussian Splattingcited by 130
- 2023Delta Denoising Scorecited by 120
- 2023Vox-E: Text-guided Voxel Editing of 3D Objectscited by 114
- 2024GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editingcited by 114
- 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidancecited by 109
- 2023Inversion-Free Image Editing with Natural Languagecited by 106
- 2023Noise-Free Score Distillationcited by 99
- 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 92
- 2023FocalDreamer: Text-driven 3D Editing via Focal-fusion Assemblycited by 75
- 2024ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fieldscited by 68
- 2023OBJECT 3DIT: Language-guided 3D-aware Image Editingcited by 62
- 2023Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversioncited by 47
- 2024Generic 3D Diffusion Adapter Using Controlled Multi-View Editingcited by 46
- 2023Posterior Distillation Samplingcited by 45
- 2024VideoMV: Consistent Multi-View Generation Based on Large Video Generative Modelcited by 45
- 2020Neural Volume Rendering: NeRF And Beyondcited by 44
- 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
- 2024RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpaintingcited by 21
- 2023Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Trainingcited by 20
- 2024Diffusion Time-step Curriculum for One Image to 3D Generationcited by 20
- 2023RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion Modelscited by 19
- 2024ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editingcited by 18
- 2023LatentEditor: Text Driven Local Editing of 3D Scenescited by 17
- 2023Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Modelscited by 16
- 2024LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernelscited by 15
- 2023High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Priorcited by 5
- 2024Freditor: High-Fidelity and Transferable NeRF Editing by Frequency Decompositioncited by 5
Built on by
Citing papers per year: 2024: 3; 2025: 4; 2026: 3.
10 papers.
- 2024EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splattingcited by 40
- 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
- 2024GRPose: Learning Graph Relations for Human Image Generation with Pose Priorscited by 14
- 2025Fast Multi-view Consistent 3D Editing with Video Priorscited by 12
- 2025AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referringcited by 10
- 2026Omni-3DEdit: Generalized Versatile 3D Editing in One-Passcited by 6
- 2024Advancing Prompt Learning through an External Layercited by 2
- 2025Advancing 3D Gaussian Splatting Editing with Complementary and Consensus Informationcited by 2
- 2026ReAge3D: Re-Aging 3D Faces with View Consistencycited by 0
- 2026LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Modelscited by 0
- 2026LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Models16 Jul 2026
- 2026ReAge3D: Re-Aging 3D Faces with View Consistency16 Jun 2026
- 2026Omni-3DEdit: Generalized Versatile 3D Editing in One-Pass18 Mar 2026
- 2025Fast Multi-view Consistent 3D Editing with Video Priors28 Nov 2025
- 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation13 Aug 2025
- 2025Advancing 3D Gaussian Splatting Editing with Complementary and Consensus Information14 Mar 2025
- 2025AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring16 Jan 2025
- 2024EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting16 Dec 2024
- 2024GRPose: Learning Graph Relations for Human Image Generation with Pose Priors29 Aug 2024
- 2024Advancing Prompt Learning through an External Layer29 Jul 2024