Search Results for author:
Found 24 papers, 9 papers with code
3D Time-lapse Reconstruction from Internet Photos
Given an Internet photo collection of a landmark, we compute a 3D time-lapse video sequence where a virtual camera moves continuously in time and space.
LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering
We take the novel approach to augment such real-time performance capture systems with a deep architecture that takes a rendering from an arbitrary viewpoint, and jointly performs completion, super resolution, and denoising of the imagery in real-time.
Neural Rerendering in the Wild
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.
Volumetric Capture of Humans with a Single RGBD Camera via Semi-Parametric Learning
The key insight is to leverage previously seen "calibration" images of a given user to extrapolate what should be rendered in a novel viewpoint from the data available in the sensor.
KeystoneDepth: Visualizing History in 3D
This paper introduces the largest and most diverse collection of rectified stereo image pairs to the research community, KeystoneDepth, consisting of tens of thousands of stereographs of historical people, events, objects, and scenes between 1860 and 1963.
Style-based Encoder Pre-training for Multi-modal Image Synthesis
Then we train a generator to transform an input image along with a style-code to the output domain.
State of the Art on Neural Rendering
Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e. g., by the integration of differentiable rendering into network training.
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs.
GeLaTO: Generative Latent Textured Objects
Accurate modeling of 3D objects exhibiting transparency, reflections and thin structures is an extremely challenging problem.
Nerfies: Deformable Neural Radiance Fields
We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones.
No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry
Removing objects from images is a challenging problem that is important for many applications, including mixed reality.
Time-Travel Rephotography
Many historical people were only ever captured by old, faded, black and white photos, that are distorted due to the limitations of early cameras and the passage of time.
ShaRF: Shape-conditioned Radiance Fields from a Single View
We demonstrate in several experiments the effectiveness of our approach in both synthetic and real images.
IBRNet: Learning Multi-View Image-Based Rendering
Unlike neural scene representation work that optimizes per-scene functions for rendering, we learn a generic view interpolation function that generalizes to novel scenes.
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
Mip-NeRF is also able to match the accuracy of a brute-force supersampled NeRF on our multiscale dataset while being 22x faster.
Neural RGB-D Surface Reconstruction
Obtaining high-quality 3D reconstructions of room-scale scenes is of paramount importance for upcoming applications in AR or VR.
FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling
We investigate the use of Neural Radiance Fields (NeRF) to learn high quality 3D object category models from collections of input images.
HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
A common approach to reconstruct such non-rigid scenes is through the use of a learned deformation field mapping from coordinates in each input image into a canonical template coordinate space.
Advances in Neural Rendering
The reconstruction of such a scene representation from observations using differentiable rendering losses is known as inverse graphics or inverse rendering.
NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
By rendering raw output images from the resulting NeRF, we can perform novel high dynamic range (HDR) view synthesis tasks.
Novel View Synthesis with Diffusion Models
We demonstrate that stochastic conditioning significantly improves the 3D consistency of a naive sampler for an image-to-image diffusion model, which involves conditioning on a single fixed view.
LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals
Finding localized correspondences across different images of the same object is crucial to understand its geometry.
SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates
To address this issue, we introduce SCADE, a novel technique that improves NeRF reconstruction quality on sparse, unconstrained input views for in-the-wild indoor scenes.
CamP: Camera Preconditioning for Neural Radiance Fields
We propose using a proxy problem to compute a whitening transform that eliminates the correlation between camera parameters and normalizes their effects, and we propose to use this transform as a preconditioner for the camera parameters during joint optimization.
