# Novel Views of Objects from a Single Image

arXiv: https://arxiv.org/abs/1602.00328 · HTML: https://mlsanity.com/paper/1602.00328/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2016.

## Built on by (most cited first, 12 of 12)

- [Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior](https://mlsanity.com/paper/2303.14184/) (2023)
- [Generalizable Neural Radiance Fields for Novel View Synthesis with Transformer](https://mlsanity.com/paper/2206.05375/) (2022)
- [Photo-to-Shape Material Transfer for Diverse Structures](https://mlsanity.com/paper/2205.04018/) (2022)
- [ID-Unet: Iterative Soft and Hard Deformation for View Synthesis](https://mlsanity.com/paper/2103.02264/) (2021)
- [TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image](https://mlsanity.com/paper/2609.04911/) (2026)
- [Robust 2D/3D Vehicle Parsing in CVIS](https://mlsanity.com/paper/2103.06432/) (2021)
- [Pose-guided Generative Adversarial Net for Novel View Action Synthesis](https://mlsanity.com/paper/2110.07993/) (2021)
- [Novel View Synthesis from a Single Image via Unsupervised learning](https://mlsanity.com/paper/2110.15569/) (2021)
- [Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks](https://mlsanity.com/paper/2111.12873/) (2021)
- [VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification](https://mlsanity.com/paper/2311.16278/) (2023)
- [Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis](https://mlsanity.com/paper/2410.04298/) (2024)
- [Depth self-supervision for single image novel view synthesis](https://mlsanity.com/paper/2308.14108/) (2023)

## Abstract (arXiv)

Taking an image of an object is at its core a lossy process. The rich information about the three-dimensional structure of the world is flattened to an image plane and decisions such as viewpoint and camera parameters are final and not easily revertible. As a consequence, possibilities of changing viewpoint are limited. Given a single image depicting an object, novel-view synthesis is the task of generating new images that render the object from a different viewpoint than the one given. The main difficulty is to synthesize the parts that are disoccluded; disocclusion occurs when parts of an object are hidden by the object itself under a specific viewpoint. In this work, we show how to improve novel-view synthesis by making use of the correlations observed in 3D models and applying them to new image instances. We propose a technique to use the structural information extracted from a 3D model that matches the image object in terms of viewpoint and shape. For the latter part, we propose an efficient 2D-to-3D alignment method that associates precisely the image appearance with the 3D model geometry with minimal user interaction. Our technique is able to simulate plausible viewpoint changes for a variety of object classes within seconds. Additionally, we show that our synthesized images can be used as additional training data that improves the performance of standard object detectors.