mlsanityData to 7 Oct 2026

Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods

arXiv 2408.04268 ↗First posted 8 Aug 2024cs.CV cs.AI cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Exploring the capabilities of Neural Radiance Fields (NeRF) and Gaussian-based methods in the context of 3D scene reconstruction, this study contrasts these modern approaches with traditional Simultaneous Localization and Mapping (SLAM) systems. Utilizing datasets such as Replica and ScanNet, we assess performance based on tracking accuracy, mapping fidelity, and view synthesis. Findings reveal that NeRF excels in view synthesis, offering unique capabilities in generating new perspectives from existing data, albeit at slower processing speeds. Conversely, Gaussian-based methods provide rapid processing and significant expressiveness but lack comprehensive scene completion. Enhanced by global optimization and loop closure techniques, newer methods like NICE-SLAM and SplaTAM not only surpass older frameworks such as ORB-SLAM2 in terms of robustness but also demonstrate superior performance in dynamic and complex environments. This comparative analysis bridges theoretical research with practical implications, shedding light on future developments in robust 3D scene reconstruction across various real-world applications.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 34 of its 51 references that are in the map. First posted on arXiv 8 Aug 2024.

Builds on

34 of 51 references.

References · 34

  1. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  2. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  3. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  4. 2023Gaussian Splatting SLAMcited by 410
  5. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  6. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  7. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  8. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  9. 2024Survival Prediction Across Diverse Cancer Types Using Neural Networkscited by 80
  10. 2024A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasonerscited by 73
  11. 2022Can Language Understand Depth?cited by 66
  12. 2023Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networkscited by 54
22 more
  1. 2024Convolutional neural network classification of cancer cytopathology images: taking breast cancer as an examplecited by 50
  2. 2024Exploring Diverse Methods in Visual Question Answeringcited by 45
  3. 2024Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformerscited by 35
  4. 2024WorDepth: Variational Language Prior for Monocular Depth Estimationcited by 34
  5. 2024Regional Style and Color Transfercited by 30
  6. 2024Credit Card Fraud Detection Using Advanced Transformer Modelcited by 26
  7. 2024DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAMcited by 22
  8. 2023Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localizationcited by 20
  9. 2024GM-DF: Generalized Multi-Scenario Deepfake Detectioncited by 16
  10. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 15
  11. 2024DeepGI: An Automated Approach for Gastrointestinal Tract Segmentation in MRI Scanscited by 13
  12. 2024RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splattingcited by 10
  13. 2024Advanced AI Framework for Enhanced Detection and Assessment of Abdominal Trauma: Integrating 3D Segmentation with 2D CNN and RNN Modelscited by 9
  14. 2023Towards Open World NeRF-Based SLAMcited by 8
  15. 2024Advanced Payment Security System:XGBoost, LightGBM and SMOTE Integratedcited by 8
  16. 2022Complex Scene Image Editing by Scene Graph Comprehensioncited by 7
  17. 2023Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledgecited by 7
  18. 2024Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translationcited by 7
  19. 2024Selective Domain-Invariant Feature for Generalizable Deepfake Detectioncited by 5
  20. 2023Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controlscited by 4
  21. 2023Transfer learning-based physics-informed convolutional neural network for simulating flow in porous media with time-varying controlscited by 4
  22. 2020Dimensionality Reduction via Diffusion Map Improved with Supervised Linear Projectioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 5; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approachcited by 24
  2. 2024NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-trainingcited by 15
  3. 2024AR Overlay: Training Image Pose Estimation on Curved Surface in a Synthetic Waycited by 15
  4. 2024Recent Advancement of Emotion Cognition in Large Language Modelscited by 9
  5. 2025Data Augmentation Through Random Style Replacementcited by 9
  6. 2024Style Transfer: From Stitching to Neural Networkscited by 8
  7. 2025NeRF-Based defect detectioncited by 7
  8. 2025Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMscited by 5
  9. 2025Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environmentscited by 4
  10. 2024Enhancing Skin Lesion Diagnosis with Ensemble Learningcited by 3
  11. 2024Enhanced Credit Score Prediction Using Ensemble Deep Learning Modelcited by 2
  12. 2024Enhancing Exchange Rate Forecasting with Explainable Deep Learning Modelscited by 2
4 more
  1. 2024Context-Aware Token Selection and Packing for Enhanced Vision Transformercited by 1
  2. 2025Modality-Aware Infrared and Visible Image Fusion with Target-Aware Supervisioncited by 1
  3. 2026Pi-GS: Sparse-View Gaussian Splatting with Dense π3 Initializationcited by 0
  4. 2026Efficient Segment Anything with Depth-Aware Fusion and Limited Training Datacited by 0