Search Results for author:
Found 21 papers, 12 papers with code
Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
To achieve this goal, we build on recent work on video diffusion, used within an autoregressive framework that can easily scale to long sequences.
Persistent Nature: A Generative Model of Unbounded 3D Worlds
Despite increasingly realistic image quality, recent 3D image generative models often operate on 3D volumes of fixed extent with limited camera motions.
Ranked #3 on
Scene Generation
on GoogleEarth
(KID metric)
DynIBaR: Neural Dynamic Image-Based Rendering
Our system retains the advantages of prior methods in its ability to model complex scenes and view-dependent effects, but also enables synthesizing photo-realistic novel views from long videos featuring complex scene dynamics with unconstrained camera trajectories.
Deformable Sprites for Unsupervised Video Decomposition
We describe a method to extract persistent elements of a dynamic scene from an input video.
Simple and Effective Synthesis of Indoor 3D Scenes
We study the problem of synthesizing immersive 3D indoor scenes from one or more images.
Dimensions of Motion: Monocular Prediction through Flow Subspaces
We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.
SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting
We present SLIDE, a modular and unified system for single image 3D photography that uses a simple yet effective soft layering strategy to better preserve appearance details in novel views.
Consistent Depth of Moving Objects in Video
We present a method to estimate depth of a dynamic scene, containing arbitrary moving objects, from an ordinary video captured with a moving camera.
KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control
We cast this as the problem of aligning a source 3D object to a target 3D object from the same object category.
De-rendering the World's Revolutionary Artefacts
Recent works have shown exciting results in unsupervised image de-rendering -- learning to decompose 3D shape, appearance, and lighting from single-image collections without explicit supervision.
Repopulating Street Scenes
We present a framework for automatically reconfiguring images of street scenes by populating, depopulating, or repopulating them with objects such as pedestrians or vehicles.
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image
We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image.
MetaSDF: Meta-learning Signed Distance Functions
Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution.
Single-View View Synthesis with Multiplane Images
A recent strand of work in view synthesis uses deep learning to generate multiplane images (a camera-centric, layered 3D representation) given two or more input images at known viewpoints.
Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illumination
We present a deep learning solution for estimating the incident illumination at any 3D location within a scene from an input narrow-baseline stereo image pair.
DeepView: View Synthesis with Learned Gradient Descent
We present a novel approach to view synthesis using multiplane images (MPIs).
Pushing the Boundaries of View Extrapolation with Multiplane Images
We present a theoretical analysis showing how the range of views that can be rendered from an MPI increases linearly with the MPI disparity sampling frequency, as well as a novel MPI prediction procedure that theoretically enables view extrapolations of up to $4\times$ the lateral viewpoint movement allowed by prior work.
Learning the Depths of Moving People by Watching Frozen People
We present a method for predicting dense depth in scenarios where both a monocular camera and people in the scene are freely moving.
Layer-structured 3D Scene Inference via View Synthesis
We present an approach to infer a layer-structured 3D representation of a scene from a single input image.
Stereo Magnification: Learning View Synthesis using Multiplane Images
The view synthesis problem--generating novel views of a scene from known imagery--has garnered recent attention due in part to compelling applications in virtual and augmented reality.
