DeepView: View Synthesis with Learned Gradient Descent
Not on the map. Why?
Abstract (arXiv)
We present a novel approach to view synthesis using multiplane images (MPIs). Building on recent advances in learned gradient descent, our algorithm generates an MPI from a set of sparse camera viewpoints. The resulting method incorporates occlusion reasoning, improving performance on challenging scene features such as object boundaries, lighting reflections, thin structures, and scenes with high depth complexity. We show that our method achieves high-quality, state-of-the-art results on two datasets: the Kalantari light field dataset, and a new camera array dataset, Spaces, which we make publicly available.
Key facts. Cited by 253 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Jun 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 70; 2022: 61; 2023: 68; 2024: 29; 2025: 14; 2026: 11.
253 papers.
Sort:
By area:
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
- 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
- 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
- 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
- 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
- 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
- 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
- 2021Advances in Neural Renderingcited by 365
- 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
38 more
- 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
- 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
- 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 274
- 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
- 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
- 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
- 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
- 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 216
- 2021Neural Articulated Radiance Fieldcited by 196
- 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 196
- 2023Robust Dynamic Radiance Fieldscited by 194
- 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
- 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 192
- 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
- 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
- 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 189
- 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 182
- 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 174
- 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
- 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
- 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
- 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
- 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
- 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
- 2022Mixed Neural Voxels for Fast Multi-view Video Synthesiscited by 127
- 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 122
- 2022Generalizable Patch-Based Neural Renderingcited by 122
- 2022Streaming Radiance Fields for 3D Video Synthesiscited by 119
- 2021Pathdreamer: A World Model for Indoor Navigationcited by 118
- 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
- 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
- 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 114
- 2022Is Attention All That NeRF Needs?cited by 113
- 2021Neural Lumigraph Renderingcited by 105
- 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
- 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 100
- 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
- 2022Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Imagecited by 88
50 most cited of 253 All 253 (JSON)
- 2026InceptionGS: Generative Bootstrapping for Large-Scale Gaussian Splatting under Unstructured View Sampling2 Sep 2026
- 20263DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis29 Jul 2026
- 2026Online Neural Space Time Memory for Dynamic Novel View Synthesis16 Jul 2026
- 2026FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows18 Jun 2026
- 2026Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image1 Jun 2026
- 2026Learn2Splat: Extending the Horizon of Learned 3DGS Optimization15 May 2026
- 2026GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens16 Apr 2026
- 2026GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis31 Mar 2026
- 2026UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling24 Feb 2026
- 2026tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction23 Feb 2026
- 2026Quantum Implicit Neural Representations for Novel View Synthesis8 Jan 2026
- 2025Sharp Monocular View Synthesis in Less Than a Second11 Dec 2025
38 more
- 2025Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment9 Dec 2025
- 2025Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap27 Oct 2025
- 2025ReSplat: Learning Recurrent Gaussian Splatting9 Oct 2025
- 2025LVT: Large-Scale Scene Reconstruction via Local View Transformers29 Sep 2025
- 2025RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting6 Aug 2025
- 2025LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures8 Jul 2025
- 2025GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis26 May 2025
- 2025Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency25 May 2025
- 2025Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization5 Apr 2025
- 2025LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene24 Mar 2025
- 2025Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting18 Mar 2025
- 2025LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh13 Feb 2025
- 2025CheapNVS: Real-Time On-Device Narrow-Baseline Novel View Synthesis24 Jan 2025
- 2024Real-Time Position-Aware View Synthesis from Single-View Input18 Dec 2024
- 2024Deformable Radial Kernel Splatting16 Dec 2024
- 2024Privacy Drift: Evolving Privacy Concerns in Incremental Learning6 Dec 2024
- 2024Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning29 Nov 2024
- 2024Quark: Real-time, High-resolution, and General Neural View Synthesis25 Nov 2024
- 2024Planar Reflection-Aware Neural Radiance Fields7 Nov 2024
- 2024Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis6 Nov 2024
- 2024Fully Explicit Dynamic Gaussian Splatting21 Oct 2024
- 2024GMT: Enhancing Generalizable Neural Rendering via Geometry-Driven Multi-Reference Texture Transfer1 Oct 2024
- 2024OPONeRF: One-Point-One NeRF for Robust Neural Rendering30 Sep 2024
- 2024G3R: Gradient Guided Generalizable Reconstruction28 Sep 2024
- 2024AIM 2024 Sparse Neural Rendering Challenge: Dataset and Benchmark23 Sep 2024
- 2024G3DST: Generalizing 3D Style Transfer with Neural Radiance Fields across Scenes and Styles24 Aug 2024
- 2024BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes22 Jul 2024
- 2024Enhancing Neural Radiance Fields with Depth and Normal Completion Priors from Sparse Views8 Jul 2024
- 2024Segment Any 4D Gaussians5 Jul 2024
- 2024Lightweight Predictive 3D Gaussian Splats27 Jun 2024
- 2024Modeling Ambient Scene Dynamics for Free-view Synthesis13 Jun 2024
- 20243DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting28 May 2024
- 2024Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels27 May 2024
- 2024Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling23 May 2024
- 2024Stereo-Knowledge Distillation from dpMV to Dual Pixels for Light Field Video Reconstruction20 May 2024
- 2024RapidVol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans16 Apr 2024
- 2024Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D27 Mar 2024
- 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenes22 Mar 2024
50 newest of 253 All 253 (JSON)
- 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 274
- 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
- 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Viewscited by 31
- 2023Free-Editor: Zero-shot Text-driven 3D Scene Editingcited by 14
- 2023Editing 3D Scenes via Text Prompts without Retrainingcited by 8
- 2023Light Field Diffusion for Single-View Novel View Synthesiscited by 3
- 2025Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gapcited by 1
- 2025Yesnt: Are Diffusion Relighting Models Ready for Capture Stage Compositing? A Hybrid Alternative to Bridge the Gap27 Oct 2025
- 2023Free-Editor: Zero-shot Text-driven 3D Scene Editing21 Dec 2023
- 2023Light Field Diffusion for Single-View Novel View Synthesis20 Sep 2023
- 2023Editing 3D Scenes via Text Prompts without Retraining10 Sep 2023
- 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views6 Jun 2023
- 2023Generative Novel View Synthesis with 3D-Aware Diffusion Models5 Apr 2023
- 2023Consistent View Synthesis with Pose-Guided Diffusion Models30 Mar 2023
- 2021Pathdreamer: A World Model for Indoor Navigationcited by 118
- 2023Persistent Nature: A Generative Model of Unbounded 3D Worldscited by 44
- 2023Persistent Nature: A Generative Model of Unbounded 3D Worlds23 Mar 2023
- 2021Pathdreamer: A World Model for Indoor Navigation18 May 2021
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
- 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
- 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
- 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
- 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
- 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
- 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
- 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
- 2021Advances in Neural Renderingcited by 365
- 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
12 most cited of 240 All 240 (JSON)
- 2026InceptionGS: Generative Bootstrapping for Large-Scale Gaussian Splatting under Unstructured View Sampling2 Sep 2026
- 20263DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis29 Jul 2026
- 2026Online Neural Space Time Memory for Dynamic Novel View Synthesis16 Jul 2026
- 2026FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows18 Jun 2026
- 2026Fast and Lightweight Novel View Synthesis with Differentiable Multiplane Image1 Jun 2026
- 2026Learn2Splat: Extending the Horizon of Learned 3DGS Optimization15 May 2026
- 2026GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens16 Apr 2026
- 2026GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis31 Mar 2026
- 2026tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction23 Feb 2026
- 2026Quantum Implicit Neural Representations for Novel View Synthesis8 Jan 2026
- 2025Sharp Monocular View Synthesis in Less Than a Second11 Dec 2025
- 2025Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment9 Dec 2025
12 newest of 240 All 240 (JSON)