Search Results for author:
Found 21 papers, 10 papers with code
Unsupervised Joint Object Discovery and Segmentation in Internet Images
In contrast to previous co-segmentation methods, our algorithm performs well even in the presence of significant amounts of noise images (images not containing a common object), as typical for datasets collected from Internet search.
Virtual Rephotography: Novel View Prediction Error for 3D Reconstruction
Furthermore, using only geometric accuracy by itself does not allow evaluating systems that either lack a geometric scene representation or utilize coarse proxy geometry.
Co-segmentation for Space-Time Co-located Collections
Thus, to disambiguate what the common foreground object is, we introduce a weakly-supervised technique, where we assume only a small seed, given in the form of a single segmented image.
DeepMVS: Learning Multi-view Stereopsis
We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction.
3D Photography using Context-aware Layered Depth Inpainting
We propose a method for converting a single RGB-D input image into a 3D photo - a multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view.
Consistent Video Depth Estimation
We present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video.
One Shot 3D Photography
3D photos are static in time, like traditional photos, but are displayed with interactive parallax on mobile or desktop screens, as well as on Virtual Reality devices, where viewing it also includes stereo.
Flow-edge Guided Video Completion
We present a new flow-based video completion algorithm.
Ranked #4 on
Video Inpainting
on DAVIS
Space-time Neural Irradiance Fields for Free-Viewpoint Video
We present a method that learns a spatiotemporal neural irradiance field for dynamic scenes from a single video.
Robust Consistent Video Depth Estimation
We present an algorithm for estimating consistent dense depth maps and camera poses from a monocular video.
Dynamic View Synthesis from Dynamic Monocular Video
We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene.
Learning Neural Light Fields with Ray-Space Embedding Networks
Our method supports rendering with a single network evaluation per pixel for small baseline light field datasets and can also be applied to larger baselines with only a few evaluations per pixel.
Boosting View Synthesis With Residual Transfer
We present a simple but effective technique to boost the rendering quality, which can be easily integrated with most view synthesis methods.
Learning Neural Light Fields With Ray-Space Embedding
Our method supports rendering with a single network evaluation per pixel for small baseline light fields and with only a few evaluations per pixel for light fields with larger baselines.
Robust Dynamic Radiance Fields
Dynamic radiance field reconstruction methods aim to model the time-varying structure and appearance of a dynamic scene.
HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling
Volumetric scene representations enable photorealistic view synthesis for static scenes and form the basis of several existing 6-DoF video techniques.
Ranked #1 on
Novel View Synthesis
on DONeRF: Evaluation Dataset
Progressively Optimized Local Radiance Fields for Robust View Synthesis
For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner.
Consistent View Synthesis with Pose-Guided Diffusion Models
In this work, we propose a pose-guided diffusion model to generate a consistent long-term video of novel views from a single image.
Single-Image 3D Human Digitization with Shape-Guided Diffusion
We present an approach to generate a 360-degree view of a person with a consistent, high-resolution appearance from a single input image.
IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images
While numerous 3D reconstruction and novel-view synthesis methods allow for photorealistic rendering of a scene from multi-view images easily captured with consumer cameras, they bake illumination in their representations and fall short of supporting advanced applications like material editing, relighting, and virtual object insertion.
Taming Latent Diffusion Model for Neural Radiance Field Inpainting
These two problems are further reinforced with the use of pixel-distance losses.
