# View Synthesis by Appearance Flow

arXiv: https://arxiv.org/abs/1605.03557 · HTML: https://mlsanity.com/paper/1605.03557/

## Key facts

- Cited by 172 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2016.

## Built on by (most cited first, 30 of 172)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior](https://mlsanity.com/paper/2303.14184/) (2023)
- [DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization](https://mlsanity.com/paper/2403.06912/) (2024)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering](https://mlsanity.com/paper/2211.11610/) (2022)
- [SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction](https://mlsanity.com/paper/2212.00792/) (2022)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering](https://mlsanity.com/paper/2112.15399/) (2021)
- [AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation](https://mlsanity.com/paper/2304.09790/) (2023)
- [StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On](https://mlsanity.com/paper/2312.01725/) (2023)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [Parser-Free Virtual Try-on via Distilling Appearance Flows](https://mlsanity.com/paper/2103.04559/) (2021)
- [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](https://mlsanity.com/paper/2104.00670/) (2021)
- [Hallucinated Neural Radiance Fields in the Wild](https://mlsanity.com/paper/2111.15246/) (2021)
- [CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization](https://mlsanity.com/paper/2311.18159/) (2023)
- [CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularization](https://mlsanity.com/paper/2405.12110/) (2024)
- [GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning](https://mlsanity.com/paper/2303.13756/) (2023)
- [Consistent View Synthesis with Pose-Guided Diffusion Models](https://mlsanity.com/paper/2303.17598/) (2023)
- [IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation](https://mlsanity.com/paper/2205.14620/) (2022)
- [Geometry-Free View Synthesis: Transformers and no 3D Priors](https://mlsanity.com/paper/2104.07652/) (2021)
- [Style-Based Global Appearance Flow for Virtual Try-On](https://mlsanity.com/paper/2204.01046/) (2022)
- [PixelSynth: Generating a 3D-Consistent Experience from a Single Image](https://mlsanity.com/paper/2108.05892/) (2021)
- [NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer](https://mlsanity.com/paper/2405.15364/) (2024)
- [GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving](https://mlsanity.com/paper/2101.06543/) (2021)
- [Single Stage Virtual Try-on via Deformable Attention Flows](https://mlsanity.com/paper/2207.09161/) (2022)
- [Behind the Scenes: Density Fields for Single View Reconstruction](https://mlsanity.com/paper/2301.07668/) (2023)
- [Advances in 3D Generation: A Survey](https://mlsanity.com/paper/2401.17807/) (2024)
- [GAN-Supervised Dense Visual Alignment](https://mlsanity.com/paper/2112.05143/) (2021)

## Abstract (arXiv)

We address the problem of novel view synthesis: given an input image, synthesizing new images of the same object or scene observed from arbitrary viewpoints. We approach this as a learning task but, critically, instead of learning to synthesize pixels from scratch, we learn to copy them from the input image. Our approach exploits the observation that the visual appearance of different views of the same instance is highly correlated, and such correlation could be explicitly learned by training a convolutional neural network (CNN) to predict appearance flows -- 2-D coordinate vectors specifying which pixels in the input view could be used to reconstruct the target view. Furthermore, the proposed framework easily generalizes to multiple input views by learning how to optimally combine single-view predictions. We show that for both objects and scenes, our approach is able to synthesize novel views of higher perceptual quality than previous CNN-based techniques.