SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image
Not on the map. Why?
Abstract (arXiv)
Recent novel view synthesis methods obtain promising results for relatively small scenes, e.g., indoor environments and scenes with a few objects, but tend to fail for unbounded outdoor scenes with a single image as input. In this paper, we introduce SAMPLING, a Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image based on improved multiplane images (MPI). Observing that depth distribution varies significantly for unbounded outdoor scenes, we employ an adaptive-bins strategy for MPI to arrange planes in accordance with each scene image. To represent intricate geometry and multi-scale details, we further introduce a hierarchical refinement branch, which results in high-quality synthesized novel views. Our method demonstrates considerable performance gains in synthesizing large-scale unbounded outdoor scenes using a single image on the KITTI dataset and generalizes well to the unseen Tanks and Temples dataset.The code and models will soon be made available.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 56 references that are in the map. First posted on arXiv 12 Sep 2023.
Builds on
45 of 56 references.
References · 45
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
- 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
- 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
- 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
- 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
- 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
- 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
33 more
- 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
- 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
- 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
- 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
- 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
- 2019Neural Point-Based Graphicscited by 327
- 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
- 2020Single-View View Synthesis with Multiplane Imagescited by 263
- 2021Urban Radiance Fieldscited by 263
- 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
- 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 229
- 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 217
- 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 216
- 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
- 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 192
- 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
- 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 168
- 2021H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motioncited by 157
- 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
- 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 137
- 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
- 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
- 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
- 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
- 2022R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesiscited by 69
- 2022Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Imagescited by 59
- 2022READ: Large-Scale Neural Scene Rendering for Autonomous Drivingcited by 51
- 2022Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Imagescited by 39
- 2022StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hintscited by 29
- 2022HST: Hierarchical Swin Transformer for Compressed Image Super-resolutioncited by 20
- 2022CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representationscited by 13
- 2022HIPA: Hierarchical Patch Transformer for Single Image Super Resolutioncited by 11
- 2022ResNeRF: Geometry-Guided Residual Neural Radiance Field for Indoor Scene Novel View Synthesiscited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.