# Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering

arXiv: https://arxiv.org/abs/2106.09548 · HTML: https://mlsanity.com/paper/2106.09548/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 66 references that are in the map.
- First posted on arXiv 17 Jun 2021.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis](https://mlsanity.com/paper/2104.00677/) (2021)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [DeepView: View Synthesis with Learned Gradient Descent](https://mlsanity.com/paper/1906.07316/) (2019)
- [NeX: Real-time View Synthesis with Neural Basis Expansion](https://mlsanity.com/paper/2103.05606/) (2021)
- [Pushing the Boundaries of View Extrapolation with Multiplane Images](https://mlsanity.com/paper/1905.00413/) (2019)
- [Cost Volume Pyramid Based Depth Inference for Multi-View Stereo](https://mlsanity.com/paper/1912.08329/) (2019)
- [Point-Based Multi-View Stereo Network](https://mlsanity.com/paper/1908.04422/) (2019)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [Neural Rerendering in the Wild](https://mlsanity.com/paper/1904.04290/) (2019)
- [Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement](https://mlsanity.com/paper/2003.13017/) (2020)
- [Extreme View Synthesis](https://mlsanity.com/paper/1812.04777/) (2018)
- [Learning to Synthesize a 4D RGBD Light Field from a Single Image](https://mlsanity.com/paper/1708.03292/) (2017)
- [Neural Point Cloud Rendering via Multi-Plane Projection](https://mlsanity.com/paper/1912.04645/) (2019)
- [EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images](https://mlsanity.com/paper/1804.02379/) (2018)
- [Light Field Spatial Super-resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization](https://mlsanity.com/paper/2004.02215/) (2020)
- [ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression](https://mlsanity.com/paper/1910.08845/) (2019)
- [Accurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions](https://mlsanity.com/paper/1708.01964/) (2017)
- [Light Field Reconstruction Using Shearlet Transform](https://mlsanity.com/paper/1509.08969/) (2015)
- [LiFF: Light Field Features in Scale and Depth](https://mlsanity.com/paper/1901.03916/) (2019)

## Built on by (most cited first, 2 of 2)

- [NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising](https://mlsanity.com/paper/2403.20034/) (2024)
- [CoDe-NeRF: Neural Rendering via Dynamic Coefficient Decomposition](https://mlsanity.com/paper/2508.06632/) (2025)

## Abstract (arXiv)

Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence. Existing methods fail to produce satisfactory results due to the limitation on inferring reliable depth information over such challenging reference conditions. With the popularization of commercial light field (LF) cameras, capturing LF images (LFIs) is as convenient as taking regular photos, and geometry information can be reliably inferred. This inspires us to use a sparse set of LF captures to render high-quality novel views globally. However, fusion of LF captures from multiple angles is challenging due to the scale inconsistency caused by various capture settings. To overcome this challenge, we propose a novel scale-consistent volume rescaling algorithm that robustly aligns the disparity probability volumes (DPV) among different captures for scale-consistent global geometry fusion. Based on the fused DPV projected to the target camera frustum, novel learning-based modules have been proposed (i.e., the attention-guided multi-scale residual fusion module, and the disparity field guided deep re-regularization module) which comprehensively regularize noisy observations from heterogeneous captures for high-quality rendering of novel LFIs. Both quantitative and qualitative experiments over the Stanford Lytro Multi-view LF dataset show that the proposed method outperforms state-of-the-art methods significantly under different experiment settings for disparity inference and LF synthesis.