mlsanityData to 7 Oct 2026

See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization

arXiv 2501.11508 ↗First posted 20 Jan 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

3D Gaussian Splatting (3DGS) has shown remarkable performance in novel view synthesis. However, its rendering quality deteriorates with sparse inphut views, leading to distorted content and reduced details. This limitation hinders its practical application. To address this issue, we propose a sparse-view 3DGS method. Given the inherently ill-posed nature of sparse-view rendering, incorporating prior information is crucial. We propose a semantic regularization technique, using features extracted from the pretrained DINO-ViT model, to ensure multi-view semantic consistency. Additionally, we propose local depth regularization, which constrains depth values to improve generalization on unseen views. Our method outperforms state-of-the-art novel view synthesis approaches, achieving up to 0.4dB improvement in terms of PSNR on the LLFF dataset, with reduced distortion and enhanced visual quality.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 20 Jan 2025.

Builds on

28 of 49 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  6. 2021Vision Transformers for Dense Predictioncited by 1,789
  7. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  9. 2020Neural Sparse Voxel Fieldscited by 959
  10. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  11. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  12. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
16 more
  1. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  2. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  3. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  4. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  5. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  6. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  7. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  8. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  9. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  10. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  11. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  12. 2023Multi-Scale 3D Gaussian Splatting for Anti-Aliased Renderingcited by 137
  13. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 111
  14. 2016Shape Completion Enabled Robotic Graspingcited by 79
  15. 2022Online Video Super-Resolution with Convolutional Kernel Bypass Graftcited by 12
  16. 2024Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 1.

8 papers.

  1. 2025DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splattingcited by 5
  2. 2025GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstructioncited by 4
  3. 2025SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative Priorscited by 3
  4. 2025AnimateScene: Camera-controllable Animation in Any Scenecited by 3
  5. 2025Multi-view Normal and Distance Guidance Gaussian Splatting for Surface Reconstructioncited by 1
  6. 2025HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warpingcited by 1
  7. 2026F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splattingcited by 1
  8. 2025Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Frameworkcited by 0