In this supplementary material, we provide additional implementation details (Appendix A) of our model and visualization of ablation studies (Appendix B) which are not included in our main paper. BARF-W, and BARF-WD are based on [2] because there is no official NeRF-W code available. The detailed architecture of UP-NeRF is shown in the Figure 1. First two authors have an equal contribution. As we mentioned in the main paper, the evaluation process entails two stages, which are test-time pose optimization and appearance optimization.

Neural Radiance Fields (NeRF) has recently gained popularity for its impressive novel view synthesis ability. This paper studies the problem of hallucinated NeRF: i.e. recovering a realistic NeRF at a different time of day from a group of tourism images. Existing solutions adopt NeRF with a controllable appearance embedding to render novel views under various conditions, but cannot render view-consistent images with an unseen appearance. To solve this problem, we present an end-to-end framework for constructing a hallucinated NeRF, dubbed as Ha-NeRF. Specifically, we propose an appearance hallucination module to handle time-varying appearances and transfer them to novel views. Considering the complex occlusions of tourism images, an anti-occlusion module is introduced to decompose the static subjects for visibility accurately. Experimental results on synthetic data and real tourism photo collections demonstrate that our method can not only hallucinate the desired appearances, but also render occlusion-free images from different views. The project and supplementary materials are available at https://rover-xingyu.github.io/Ha-NeRF/.

Here I will tell you about "NERF in the wild" a research presented in August 2020 and which has all the features to revolutionize some application areas starting from ** Augmented and Virtual Reality **. The aim of the research is to produce a 3D visual synthesis of places starting from photographs of the same place very different from each other, taken at different times and with the automatic removal of objects / people that are not relevant to the object (done by the neural network itself during the process). Eg. the video of the Trevi fountain below was generated by NERF-W starting from public domain photographs on the Web and as you can see it was not only reproduced three-dimensionally but it is also possible to see it at different times of the day with different lights. Obviously all the tourists, cars, any advertising billboards, have been cleaned up. The intuition in this case is balanced between the use of a "standard" neural network, ie not a CNN or 3D-CNN (Convolutional Neural Networks -- born to be able to process photos / videos), and the basic rules of optics.

Historically, human artists have been challenged to recreate real-world locations as 3D models, particularly when applications call for photorealistic accuracy. But Google researchers have come up with an alternative that could simultaneously automate the 3D modeling process and improve its results, using a neural network with crowdsourced photos of a location to convincingly replicate landmarks and lighting in 3D. The idea behind neural radiance fields (NeRF) is to extract 3D depth data from 2D images by determining where light rays terminate, a sophisticated technique that alone can create plausible textured 3D models of landmarks. Google's NeRF in the Wild (NeRF-W) system goes further in several ways. First, it uses "in-the-wild photo collections" as inputs, expanding a computer's ability to see landmarks from multiple angles. Next, it evaluates the images to find structures, separating out photographic and environmental variations such as image exposure, scene lighting, post-processing, and weather conditions, as well as shot-to-shot object differences such as people who might be in one image but not another.