In this work, we explore how to leverage the success of implicit novel view synthesis methods for surface reconstruction. Methods which learn a neural radiance field have shown amazing image synthesis results, but the underlying geometry representati
on is only a coarse approximation of the real geometry. We demonstrate how depth measurements can be incorporated into the radiance field formulation to produce more detailed and complete reconstruction results than using methods based on either color or depth data alone. In contrast to a density field as the underlying geometry representation, we propose to learn a deep neural network which stores a truncated signed distance field. Using this representation, we show that one can still leverage differentiable volume rendering to estimate color values of the observed images during training to compute a reconstruction loss. This is beneficial for learning the signed distance field in regions with missing depth measurements. Furthermore, we correct misalignment errors of the camera, improving the overall reconstruction quality. In several experiments, we showcase our method and compare to existing works on classical RGB-D fusion and learned representations.
We explore total scene capture -- recording, modeling, and rerendering a scene under varying appearance such as season and time of day. Starting from internet photos of a tourist landmark, we apply traditional 3D reconstruction to register the photos
and approximate the scene as a point cloud. For each photo, we render the scene points into a deep framebuffer, and train a neural network to learn the mapping of these initial renderings to the actual photos. This rerendering network also takes as input a latent appearance vector and a semantic mask indicating the location of transient objects like pedestrians. The model is evaluated on several datasets of publicly available images spanning a broad range of illumination conditions. We create short videos demonstrating realistic manipulation of the image viewpoint, appearance, and semantic labeling. We also compare results with prior work on scene reconstruction from internet photos.
High-level manipulation of facial expressions in images --- such as changing a smile to a neutral expression --- is challenging because facial expression changes are highly non-linear, and vary depending on the appearance of the face. We present a fu
lly automatic approach to editing faces that combines the advantages of flow-based face manipulation with the more recent generative capabilities of Variational Autoencoders (VAEs). During training, our model learns to encode the flow from one expression to another over a low-dimensional latent space. At test time, expression editing can be done simply using latent vector arithmetic. We evaluate our methods on two applications: 1) single-image facial expression editing, and 2) facial expression interpolation between two images. We demonstrate that our method generates images of higher perceptual quality than previous VAE and flow-based methods.
We present a system to capture video footage of human subjects in the real world. Our system leverages a quadrotor camera to automatically capture well-composed video of two subjects. Subjects are tracked in a large-scale outdoor environment using RT
K GPS and IMU sensors. Then, given the tracked state of our subjects, our system automatically computes static shots based on well-established visual composition principles and canonical shots from cinematography literature. To transition between these static shots, we calculate feasible, safe, and visually pleasing transitions using a novel real-time trajectory planning algorithm. We evaluate the performance of our tracking system, and experimentally show that RTK GPS significantly outperforms conventional GPS in capturing a variety of canonical shots. Lastly, we demonstrate our system guiding a consumer quadrotor camera autonomously capturing footage of two subjects in a variety of use cases. This is the first end-to-end system that enables people to leverage the mobility of quadrotors, as well as the knowledge of expert filmmakers, to autonomously capture high-quality footage of people in the real world.
Sculptors often deviate from geometric accuracy in order to enhance the appearance of their sculpture. These subtle stylizations may emphasize anatomy, draw the viewers focus to characteristic features of the subject, or symbolize textures that might
not be accurately reproduced in a particular sculptural medium, while still retaining fidelity to the unique proportions of an individual. In this work we demonstrate an interactive system for enhancing face geometry using a class of stylizations based on visual decomposition into abstract semantic regions, which we call sculptural abstraction. We propose an interactive two-scale optimization framework for stylization based on sculptural abstraction, allowing real-time adjustment of both global and local parameters. We demonstrate this systems effectiveness in enhancing physical 3D prints of scans from various sources.
