mlsanityData to 7 Oct 2026

VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinement

arXiv 2601.13664 ↗First posted 20 Jan 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose VIAFormer, a Voxel-Image Alignment Transformer model designed for Multi-view Conditioned Voxel Refinement--the task of repairing incomplete noisy voxels using calibrated multi-view images as guidance. Its effectiveness stems from a synergistic design: an Image Index that provides explicit 3D spatial grounding for 2D image tokens, a Correctional Flow objective that learns a direct voxel-refinement trajectory, and a Hybrid Stream Transformer that enables robust cross-modal fusion. Experiments show that VIAFormer establishes a new state of the art in correcting both severe synthetic corruptions and realistic artifacts on the voxel shape obtained from powerful Vision Foundation Models. Beyond benchmarking, we demonstrate VIAFormer as a practical and reliable bridge in real-world 3D creation pipelines, paving the way for voxel-based methods to thrive in large-model, big-data wave.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 44 of its 49 references that are in the map. First posted on arXiv 20 Jan 2026.

Builds on

44 of 49 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  8. 2022Flow Matching for Generative Modelingcited by 5,426
  9. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  11. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  12. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
32 more
  1. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  2. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  3. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  4. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  5. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  6. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  7. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  8. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  9. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  10. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 334
  11. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  12. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  13. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  14. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  15. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  16. 2023Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigationcited by 162
  17. 2024StableNormal: Reducing Diffusion Variance for Stable and Sharp Normalcited by 153
  18. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  19. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 95
  20. 2024Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoderscited by 93
  21. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
  22. 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 57
  23. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  24. 2024Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Modelscited by 45
  25. 2025Dens3R: A Foundation Model for 3D Geometry Predictioncited by 44
  26. 2023DiffComplete: Diffusion-based Generative 3D Shape Completioncited by 35
  27. 2025ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generationcited by 30
  28. 2022PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categoriescited by 21
  29. 2025Cube: A Roblox View of 3D Intelligencecited by 14
  30. 2025Orientation Matters: Making 3D Generative Models Orientation-Alignedcited by 13
  31. 2025Demystifying Flux Architecturecited by 9
  32. 20243D Shape Completion on Unseen Categories:A Weakly-supervised Approachcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generationcited by 0