mlsanityData to 14 Oct 2026

Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling

arXiv 2510.23605 ↗First posted 27 Oct 2025cs.CV cs.AI cs.GRcited by 2

Not on the map. Why?

Abstract (arXiv)

Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one or few images of a specific subject (also known as Personalization or Subject-driven generation) allows generating visual content that align with the identity of the subject. However, personalized 3D/4D generation is still largely underexplored. In this work, we introduce TIRE (Track, Inpaint, REsplat), a novel method for subject-driven 3D/4D generation. It takes an initial 3D asset produced by an existing 3D generative model as input and uses video tracking to identify the regions that need to be modified. Then, we adopt a subject-driven 2D inpainting model for progressively infilling the identified regions. Finally, we resplat the modified 2D multi-view observations back to 3D while still maintaining consistency. Extensive experiments demonstrate that our approach significantly improves identity preservation in 3D/4D generation compared to state-of-the-art methods. Our project website is available at https://zsh2000.github.io/track-inpaint-resplat.github.io/.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 126 of its 132 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

126 of 132 references.

References · 126

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2025Qwen2.5-VL Technical Reportcited by 5,587
  9. 2024GPT-4o System Cardcited by 4,588
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  11. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  12. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
38 more
  1. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  2. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  4. 2025Gemma 3 Technical Reportcited by 1,824
  5. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  6. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  7. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  9. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 985
  10. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  11. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  12. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  13. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  14. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  15. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  16. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  17. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  18. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  19. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  20. 2023CoTracker: It is Better to Track Togethercited by 522
  21. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 521
  22. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  23. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  24. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  25. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  26. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  27. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  28. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  29. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  30. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  31. 2023InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuningcited by 345
  32. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attentioncited by 313
  33. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  34. 2022Novel View Synthesis with Diffusion Modelscited by 300
  35. 2023Text-to-3D using Gaussian Splattingcited by 299
  36. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  37. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 257
  38. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 235

50 most cited of 126 All 126 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Full-4D: Generating Full-Scope 4D Scenes from a Single-View Videocited by 5
  2. 2026Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generationcited by 0