# Learning 3D Photography Videos via Self-supervised Diffusion on Single Images

arXiv: https://arxiv.org/abs/2302.10781 · HTML: https://mlsanity.com/paper/2302.10781/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 41 references that are in the map.
- First posted on arXiv 21 Feb 2023.

## Builds on (most cited first, 30 of 35)

- [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)
- [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)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://mlsanity.com/paper/2210.02399/) (2022)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Single-View View Synthesis with Multiplane Images](https://mlsanity.com/paper/2004.11364/) (2020)
- [GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions](https://mlsanity.com/paper/2104.14806/) (2021)
- [SEAN: Image Synthesis with Semantic Region-Adaptive Normalization](https://mlsanity.com/paper/1911.12861/) (2019)
- [Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image](https://mlsanity.com/paper/2012.09855/) (2020)
- [3D Photography using Context-aware Layered Depth Inpainting](https://mlsanity.com/paper/2004.04727/) (2020)
- [MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis](https://mlsanity.com/paper/2103.14910/) (2021)
- [Semantic Image Synthesis via Diffusion Models](https://mlsanity.com/paper/2207.00050/) (2022)
- [3D Ken Burns Effect from a Single Image](https://mlsanity.com/paper/1909.05483/) (2019)
- [Learning the Depths of Moving People by Watching Frozen People](https://mlsanity.com/paper/1904.11111/) (2019)
- [Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis](https://mlsanity.com/paper/1910.06809/) (2019)
- [PixelSynth: Generating a 3D-Consistent Experience from a Single Image](https://mlsanity.com/paper/2108.05892/) (2021)
- [InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images](https://mlsanity.com/paper/2207.11148/) (2022)
- [Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image](https://mlsanity.com/paper/2012.09854/) (2020)
- [NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis](https://mlsanity.com/paper/2207.09814/) (2022)
- [Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images](https://mlsanity.com/paper/2205.11733/) (2022)
- [Efficient Semantic Image Synthesis via Class-Adaptive Normalization](https://mlsanity.com/paper/2012.04644/) (2020)

## Built on by (most cited first, 8 of 8)

- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix](https://mlsanity.com/paper/2407.00367/) (2024)
- [FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection](https://mlsanity.com/paper/2407.13133/) (2024)
- [SpatialDreamer: Self-supervised Stereo Video Synthesis from Monocular Input](https://mlsanity.com/paper/2411.11934/) (2024)
- [M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion](https://mlsanity.com/paper/2505.16565/) (2025)
- [LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model](https://mlsanity.com/paper/2506.01546/) (2025)
- [Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views](https://mlsanity.com/paper/2601.03362/) (2026)
- [S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix](https://mlsanity.com/paper/2508.08048/) (2025)

## Abstract (arXiv)

3D photography renders a static image into a video with appealing 3D visual effects. Existing approaches typically first conduct monocular depth estimation, then render the input frame to subsequent frames with various viewpoints, and finally use an inpainting model to fill those missing/occluded regions. The inpainting model plays a crucial role in rendering quality, but it is normally trained on out-of-domain data. To reduce the training and inference gap, we propose a novel self-supervised diffusion model as the inpainting module. Given a single input image, we automatically construct a training pair of the masked occluded image and the ground-truth image with random cycle-rendering. The constructed training samples are closely aligned to the testing instances, without the need of data annotation. To make full use of the masked images, we design a Masked Enhanced Block (MEB), which can be easily plugged into the UNet and enhance the semantic conditions. Towards real-world animation, we present a novel task: out-animation, which extends the space and time of input objects. Extensive experiments on real datasets show that our method achieves competitive results with existing SOTA methods.