Search Results for author:
Found 25 papers, 10 papers with code
Text2LIVE: Text-Driven Layered Image and Video Editing
Given an input image or video and a target text prompt, our goal is to edit the appearance of existing objects (e. g., object's texture) or augment the scene with visual effects (e. g., smoke, fire) in a semantically meaningful manner.
Volume Rendering of Neural Implicit Surfaces
Accurate sampling is important to provide a precise coupling of geometry and radiance; and (iii) it allows efficient unsupervised disentanglement of shape and appearance in volume rendering.
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
In this work we address the challenging problem of multiview 3D surface reconstruction.
Layered Neural Atlases for Consistent Video Editing
We present a method that decomposes, or "unwraps", an input video into a set of layered 2D atlases, each providing a unified representation of the appearance of an object (or background) over the video.
On the Similarity between the Laplace and Neural Tangent Kernels
Experiments show that these kernel methods perform similarly to real neural networks.
Deep Permutation Equivariant Structure from Motion
Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i. e., when cameras are both internally and externally calibrated.
Training-Free Consistent Text-to-Image Generation
Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language.
GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matrices
First, given ${n \choose 2}$ fundamental matrices computed for $n$ images, we provide a complete algebraic characterization in the form of conditions that are both necessary and sufficient to enabling the recovery of camera matrices.
The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
We study the relationship between the frequency of a function and the speed at which a neural network learns it.
Resultant Based Incremental Recovery of Camera Pose from Pairwise Matches
In this paper, we introduce a novel solution to the six-point online algorithm to recover the exterior parameters associated with $I_n$.
Camera Calibration from Dynamic Silhouettes Using Motion Barcodes
The use of motion barcodes leads to increased speed, accuracy, and robustness in computing the epipolar geometry.
Fundamental Matrices from Moving Objects Using Line Motion Barcodes
Corresponding epipolar lines have similar motion barcodes, and candidate pairs of corresponding epipoar lines are found by the similarity of their motion barcodes.
Two view constraints on the epipoles from few correspondences
We show how it can be used to reduce the number of required points for the epipolar geometry when some information about the epipoles is available and demonstrate this with a buddy search app.
Algebraic Characterization of Essential Matrices and Their Averaging in Multiview Settings
A common approach to essential matrix averaging is to separately solve for camera orientations and subsequently for camera positions.
Averaging Essential and Fundamental Matrices in Collinear Camera Settings
Global methods to Structure from Motion have gained popularity in recent years.
Frequency Bias in Neural Networks for Input of Non-Uniform Density
Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from a uniform distribution find a low frequency fit before high frequency ones.
End-To-End Convolutional Neural Network for 3D Reconstruction of Knee Bones From Bi-Planar X-Ray Images
In contrast to the common approach of statistically modeling the shape of each bone, our deep network learns the distribution of the bones' shapes directly from the training images.
Neural Congealing: Aligning Images to a Joint Semantic Atlas
We present Neural Congealing -- a zero-shot self-supervised framework for detecting and jointly aligning semantically-common content across a given set of images.
Neural LiDAR Fields for Novel View Synthesis
We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements, with the goal of synthesizing realistic LiDAR scans from novel viewpoints.
CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
In this work, we present Conditional Adversarial Latent Models (CALM), an approach for generating diverse and directable behaviors for user-controlled interactive virtual characters.
Point-Cloud Completion with Pretrained Text-to-image Diffusion Models
Point-cloud data collected in real-world applications are often incomplete.
Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer
This loss guides the generation process to preserve the overall motion of the input video while complying with the target object in terms of shape and fine-grained motion traits.
SceneScape: Text-Driven Consistent Scene Generation
We present a method for text-driven perpetual view generation -- synthesizing long-term videos of various scenes solely, given an input text prompt describing the scene and camera poses.
Learning Priors for Non Rigid SfM from Casual Videos
We tackle the long-standing challenge of reconstructing 3D structures and camera positions from videos.
RESFM: Robust Equivariant Multiview Structure from Motion
Multiview Structure from Motion is a fundamental and challenging computer vision problem.
