# Novel View Synthesis with Pixel-Space Diffusion Models

arXiv: https://arxiv.org/abs/2411.07765 · HTML: https://mlsanity.com/paper/2411.07765/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 53 of its 61 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023)
- [ReconFusion: 3D Reconstruction with Diffusion Priors](https://mlsanity.com/paper/2312.02981/) (2023)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)

## Built on by (most cited first, 16 of 16)

- [InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems](https://mlsanity.com/paper/2504.01689/) (2025)
- [LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation](https://mlsanity.com/paper/2509.08628/) (2025)
- [Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesis](https://mlsanity.com/paper/2511.12675/) (2025)
- [Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis](https://mlsanity.com/paper/2511.13011/) (2025)
- [Pixel-Space Diffusion Transformers](https://mlsanity.com/paper/2607.17585/) (2026)
- [Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models](https://mlsanity.com/paper/2607.19120/) (2026)
- [Novel View Synthesis using DDIM Inversion](https://mlsanity.com/paper/2508.10688/) (2025)
- [Align-cDAE: Alzheimer's Disease Progression Modeling with Attention-Aligned Conditional Diffusion Auto-Encoder](https://mlsanity.com/paper/2603.01552/) (2026)
- [One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation](https://mlsanity.com/paper/2603.23488/) (2026)
- [3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis](https://mlsanity.com/paper/2604.11211/) (2026)
- [RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video](https://mlsanity.com/paper/2605.31535/) (2026)
- [GenRec: Knowing Where to Reconstruct and Where to Generate](https://mlsanity.com/paper/2608.17832/) (2026)
- [Stabilizing Camera-Controlled Novel View Synthesis at Inference Time](https://mlsanity.com/paper/2609.03639/) (2026)
- [Geometric Inconsistency Localization in Multi-View Image Sets](https://mlsanity.com/paper/2609.31247/) (2026)
- [VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis](https://mlsanity.com/paper/2609.33253/) (2026)
- [PartiCam: Camera Controlled Video Generation with Reward Guidance](https://mlsanity.com/paper/2609.39504/) (2026)

## Abstract (arXiv)

Synthesizing a novel view from a single input image is a challenging task. Traditionally, this task was approached by estimating scene depth, warping, and inpainting, with machine learning models enabling parts of the pipeline. More recently, generative models are being increasingly employed in novel view synthesis (NVS), often encompassing the entire end-to-end system. In this work, we adapt a modern diffusion model architecture for end-to-end NVS in the pixel space, substantially outperforming previous state-of-the-art (SOTA) techniques. We explore different ways to encode geometric information into the network. Our experiments show that while these methods may enhance performance, their impact is minor compared to utilizing improved generative models. Moreover, we introduce a novel NVS training scheme that utilizes single-view datasets, capitalizing on their relative abundance compared to their multi-view counterparts. This leads to improved generalization capabilities to scenes with out-of-domain content.