mlsanityData to 14 Oct 2026

DGNS: Deformable Gaussian Splatting and Dynamic Neural Surface for Monocular Dynamic 3D Reconstruction

arXiv 2412.03910 ↗First posted 5 Dec 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Dynamic scene reconstruction from monocular video is essential for real-world applications. We introduce DGNS, a hybrid framework integrating underlineDeformable underlineGaussian Splatting and Dynamic underlineNeural underlineSurfaces, effectively addressing dynamic novel-view synthesis and 3D geometry reconstruction simultaneously. During training, depth maps generated by the deformable Gaussian splatting module guide the ray sampling for faster processing and provide depth supervision within the dynamic neural surface module to improve geometry reconstruction. Conversely, the dynamic neural surface directs the distribution of Gaussian primitives around the surface, enhancing rendering quality. In addition, we propose a depth-filtering approach to further refine depth supervision. Extensive experiments conducted on public datasets demonstrate that DGNS achieves state-of-the-art performance in 3D reconstruction, along with competitive results in novel-view synthesis.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 49 of its 84 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

49 of 84 references.

References · 49

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2016Density estimation using Real NVPcited by 2,042
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  6. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  8. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  9. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  10. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  11. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  12. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
37 more
  1. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  2. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
  3. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  4. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  5. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  6. 2019Neural Point-Based Graphicscited by 327
  7. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 312
  8. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  9. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  10. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  11. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  12. 2021Neural Head Avatars from Monocular RGB Videoscited by 213
  13. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  14. 2017Dual-Path Convolutional Image-Text Embeddings with Instance Losscited by 145
  15. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  16. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 116
  17. 2023Grid-guided Neural Radiance Fields for Large Urban Scenescited by 100
  18. 2024Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstructioncited by 100
  19. 2023Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmarkcited by 75
  20. 2022MonoNeRF: Learning a Generalizable Dynamic Radiance Field from Monocular Videoscited by 63
  21. 2022Learning Granularity-Unified Representations for Text-to-Image Person Re-identificationcited by 62
  22. 2021TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Searchcited by 57
  23. 2023RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Searchcited by 54
  24. 2018Pose-Guided Multi-Granularity Attention Network for Text-Based Person Searchcited by 52
  25. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 49
  26. 2023Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstructioncited by 43
  27. 2022CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrievalcited by 39
  28. 2022Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifoldcited by 38
  29. 2023An Empirical Study of CLIP for Text-based Person Searchcited by 38
  30. 2021AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identificationcited by 34
  31. 2022OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstructioncited by 27
  32. 2024GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyondcited by 25
  33. 2024DynaSurfGS: Dynamic Surface Reconstruction with Planar-based Gaussian Splattingcited by 19
  34. 2023Text-based Person Search without Parallel Image-Text Datacited by 17
  35. 2023Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Modelcited by 10
  36. 2021Person Retrieval in Surveillance Using Textual Query: A Reviewcited by 6
  37. 2023IIITD-20K: Dense captioning for Text-Image ReIDcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 14
  2. 2025Structural Energy-Guided Sampling for View-Consistent Text-to-3Dcited by 1
  3. 2026textit4DSurf: High-Fidelity Dynamic Scene Surface Reconstructioncited by 1
  4. 20263D-IDE: 3D Implicit Depth Emergentcited by 1
  5. 2026DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functionscited by 1
  6. 2026Structural Energy Guidance for View-Consistent Text-to-3D Generationcited by 0
  7. 2026ToCo-Mesh: Topology-Consistent Dynamic Mesh Reconstruction via Adaptive Tessellation and Surface-Aligned 2DGScited by 0