mlsanityData to 7 Oct 2026

HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors

arXiv 2406.12459 ↗First posted 18 Jun 2024cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 105 of its 117 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

105 of 117 references.

References · 105

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  8. 2022Classifier-Free Diffusion Guidancecited by 5,717
  9. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  12. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
38 more
  1. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  2. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  4. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  5. 2017Mixed Precision Trainingcited by 1,135
  6. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  7. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  8. 2017End-to-end Recovery of Human Shape and Posecited by 883
  9. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  10. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  13. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 683
  14. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  15. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  16. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  17. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  18. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  19. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 516
  20. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  21. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  22. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  23. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  24. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  25. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  26. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  27. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  28. 2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
  29. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  30. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  31. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  32. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  33. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  34. 2019Multi-Garment Net: Learning to Dress 3D People from Imagescited by 244
  35. 2018Video Based Reconstruction of 3D People Modelscited by 237
  36. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  37. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  38. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214

50 most cited of 105 All 105 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 32; 2026: 18.

54 papers.

Sort:

By area:

  1. 2025LHM: Large Animatable Human Reconstruction Model from a Single Image in Secondscited by 61
  2. 2025DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generationcited by 49
  3. 2024AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstructioncited by 36
  4. 2025GUAVA: Generalizable Upper Body 3D Gaussian Avatarcited by 22
  5. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  6. 2025HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restorationcited by 13
  7. 2025RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Imagescited by 12
  8. 2024GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformerscited by 11
  9. 2025LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Meshcited by 11
  10. 2025HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformerscited by 9
  11. 2025PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modelingcited by 8
  12. 2025MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstructioncited by 8
38 more
  1. 2025HumanGif: Single-View Human Diffusion with Generative Priorcited by 7
  2. 2025Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Modelscited by 7
  3. 2025WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstructioncited by 6
  4. 2025CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Imagecited by 6
  5. 2025FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformerscited by 6
  6. 2024StdGEN: Semantic-Decomposed 3D Character Generation from Single Imagescited by 5
  7. 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modelingcited by 5
  8. 2024EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Multi-view Camera Settingscited by 4
  9. 2025DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Imagecited by 4
  10. 2025Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatarscited by 4
  11. 2025R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatarscited by 3
  12. 2025Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modelingcited by 3
  13. 2025Bringing Your Portrait to 3D Presencecited by 3
  14. 2025PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Imagecited by 2
  15. 2025Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Millisecondscited by 2
  16. 2025FlexAvatar: Flexible Large Reconstruction Model for Animatable Gaussian Head Avatars with Detailed Deformationcited by 2
  17. 2026AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priorscited by 2
  18. 2025Learning Efficient and Generalizable Human Representation with Human Gaussian Modelcited by 1
  19. 2026LayerGS: Decomposition and Inpainting of Layered 3D Human Avatars via 2D Gaussian Splattingcited by 1
  20. 2026StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generationcited by 1
  21. 2026PEAR: Pixel-aligned Expressive humAn mesh Recoverycited by 1
  22. 2026TeHOR: Text-Guided 3D Human and Object Reconstruction with Texturescited by 1
  23. 2026HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Videocited by 1
  24. 2025STGA: Selective-Training Gaussian Head Avatarscited by 0
  25. 2025CTRL-GS: Cascaded Temporal Residue Learning for 4D Gaussian Splattingcited by 0
  26. 2025DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspectivecited by 0
  27. 2025Dream3DAvatar: Text-Controlled 3D Avatar Reconstruction from a Single Imagecited by 0
  28. 2025HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentationcited by 0
  29. 2025NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Posescited by 0
  30. 2025Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinementcited by 0
  31. 2026Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusioncited by 0
  32. 2026One-Shot Feed-Forward 360circ Animatable Avatar via Inpainted UV-Space Gaussian Modelingcited by 0
  33. 2026PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstructioncited by 0
  34. 2026Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wildcited by 0
  35. 2026GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updatescited by 0
  36. 2026F3G-Avatar : Face Focused Full-body Gaussian Avatarcited by 0
  37. 2026SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splattingcited by 0
  38. 2026HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Imagecited by 0

50 most cited of 54 All 54 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
  2. 2024Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Models
  3. 2024Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors
  4. 20262Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting
  5. 2026VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors
  6. 2024GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction
  7. 2024Generalizable Human Gaussians from Single-View Image
  8. 2026Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting