mlsanityData to 14 Oct 2026

Voxify3D: Pixel Art Meets Volumetric Rendering

arXiv 2512.07834 ↗First posted 8 Dec 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Voxel art is a distinctive stylization widely used in games and digital media, yet automated generation from 3D meshes remains challenging due to conflicting requirements of geometric abstraction, semantic preservation, and discrete color coherence. Existing methods either over-simplify geometry or fail to achieve the pixel-precise, palette-constrained aesthetics of voxel art. We introduce Voxify3D, a differentiable two-stage framework bridging 3D mesh optimization with 2D pixel art supervision. Our core innovation lies in the synergistic integration of three components: (1) orthographic pixel art supervision that eliminates perspective distortion for precise voxel-pixel alignment; (2) patch-based CLIP alignment that preserves semantics across discretization levels; (3) palette-constrained Gumbel-Softmax quantization enabling differentiable optimization over discrete color spaces with controllable palette strategies. This integration addresses fundamental challenges: semantic preservation under extreme discretization, pixel-art aesthetics through volumetric rendering, and end-to-end discrete optimization. Experiments show superior performance (37.12 CLIP-IQA, 77.90% user preference) across diverse characters and controllable abstraction (2-8 colors, 20x-50x resolutions). Project page: https://yichuanh.github.io/Voxify-3D/

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 88 of its 118 references that are in the map. First posted on arXiv 8 Dec 2025.

Builds on

88 of 118 references.

References · 88

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2017Neural Discrete Representation Learningcited by 4,712
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  8. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  9. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  10. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  11. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  12. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
38 more
  1. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  2. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  3. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  4. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  6. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  7. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  8. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
  9. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  10. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  12. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
  13. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  14. 2021ClipCap: CLIP Prefix for Image Captioningcited by 559
  15. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  16. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  17. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  18. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  19. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  20. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  21. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  22. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 334
  23. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  24. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  25. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 222
  26. 2023Robust Dynamic Radiance Fieldscited by 194
  27. 2023XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchiescited by 189
  28. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 187
  29. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 135
  30. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  31. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  32. 2022NeRF-Art: Text-Driven Neural Radiance Fields Stylizationcited by 126
  33. 2023Vox-E: Text-guided Voxel Editing of 3D Objectscited by 115
  34. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Modelscited by 112
  35. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  36. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  37. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 94
  38. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Stroke of Surprise: Progressive Semantic Illusions in Vector Sketchingcited by 3
  2. 2026ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildabilitycited by 1
  3. 2026JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoisingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Native and Compact Structured Latents for 3D Generation
  2. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  3. 2025Art3D: Training-Free 3D Generation from Flat-Colored Illustration
  4. 2023Consistent Mesh Diffusion
  5. 2024MaPa: Text-driven Photorealistic Material Painting for 3D Shapes
  6. 2025MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation
  7. 2025LATTICE: Democratize High-Fidelity 3D Generation at Scale
  8. 2025End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards