Search Results for author:
Found 55 papers, 23 papers with code
3D Gaussian Splatting as Markov Chain Monte Carlo
While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which does not always generalize and may lead to poor-quality renderings.
Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience.
Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models
Further, we leverage the findings that different timesteps of the diffusion process cater to different levels of detail in an image.
Densify Your Labels: Unsupervised Clustering with Bipartite Matching for Weakly Supervised Point Cloud Segmentation
We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations while achieving the performance of recent fully supervised approaches.
PointNeRF++: A multi-scale, point-based Neural Radiance Field
We overcome these problems with a simple representation that aggregates point clouds at multiple scale levels with sparse voxel grids at different resolutions.
ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models
Thus, to perform novel-view synthesis, we create a smooth camera trajectory to the target view that we wish to render, and denoise using both a view-conditioned diffusion model and a video diffusion model.
Volumetric Rendering with Baked Quadrature Fields
We propose a novel Neural Radiance Field (NeRF) representation for non-opaque scenes that allows fast inference by utilizing textured polygons.
Unsupervised Keypoints from Pretrained Diffusion Models
Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable.
Ranked #1 on
Unsupervised Human Pose Estimation
on Tai-Chi-HD
Accelerating Neural Field Training via Soft Mining
We present an approach to accelerate Neural Field training by efficiently selecting sampling locations.
INVE: Interactive Neural Video Editing
We present Interactive Neural Video Editing (INVE), a real-time video editing solution, which can assist the video editing process by consistently propagating sparse frame edits to the entire video clip.
Unsupervised Semantic Correspondence Using Stable Diffusion
Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images.
Ranked #1 on
Semantic correspondence
on PF-WILLOW
PPDONet: Deep Operator Networks for Fast Prediction of Steady-State Solutions in Disk-Planet Systems
We develop a tool, which we name Protoplanetary Disk Operator Network (PPDONet), that can predict the solution of disk-planet interactions in protoplanetary disks in real-time.
BlendFields: Few-Shot Example-Driven Facial Modeling
Generating faithful visualizations of human faces requires capturing both coarse and fine-level details of the face geometry and appearance.
Pointersect: Neural Rendering with Cloud-Ray Intersection
Specifically, we train a set transformer that, given a small number of local neighbor points along a light ray, provides the intersection point, the surface normal, and the material blending weights, which are used to render the outcome of this light ray.
CN-DHF: Compact Neural Double Height-Field Representations of 3D Shapes
We introduce CN-DHF (Compact Neural Double-Height-Field), a novel hybrid neural implicit 3D shape representation that is dramatically more compact than the current state of the art.
FaceLit: Neural 3D Relightable Faces
We propose a generative framework, FaceLit, capable of generating a 3D face that can be rendered at various user-defined lighting conditions and views, learned purely from 2D images in-the-wild without any manual annotation.
Neural Fourier Filter Bank
We present a novel method to provide efficient and highly detailed reconstructions.
Bootstrapping Human Optical Flow and Pose
We propose a bootstrapping framework to enhance human optical flow and pose.
Attention Beats Concatenation for Conditioning Neural Fields
Neural fields model signals by mapping coordinate inputs to sampled values.
Estimating Visual Information From Audio Through Manifold Learning
Therefore, audio-based methods can be useful even for applications in which only visual information is of interest Our framework is based on Manifold Learning and consists of two steps.
NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
We introduce a method for instance proposal generation for 3D point clouds.
TUSK: Task-Agnostic Unsupervised Keypoints
Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e. g. elbow, digit, abstract geometric shape) appears only once in an image.
FlowNet-PET: Unsupervised Learning to Perform Respiratory Motion Correction in PET Imaging
To correct for respiratory motion in PET imaging, an interpretable and unsupervised deep learning technique, FlowNet-PET, was constructed.
A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset
While the quality of this pseudo-ground-truth is challenging to assess due to the lack of actual ground-truth SMPL, with the Human 3. 6m dataset, we qualitatively show that our joint locations are more accurate and that our regressor leads to improved pose estimations results on the test set without any need for retraining.
NeuMan: Neural Human Radiance Field from a Single Video
Photorealistic rendering and reposing of humans is important for enabling augmented reality experiences.
Kubric: A scalable dataset generator
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping
We propose a novel optimization framework that crops a given image based on user description and aesthetics.
CoNeRF: Controllable Neural Radiance Fields
We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i. e. camera control).
Layered Controllable Video Generation
In the first stage, with the rich set of losses and dynamic foreground size prior, we learn how to separate the frame into foreground and background layers and, conditioned on these layers, how to generate the next frame using VQ-VAE generator.
LOLNeRF: Learn from One Look
We present a method for learning a generative 3D model based on neural radiance fields, trained solely from data with only single views of each object.
MIST: Multiple Instance Spatial Transformer
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts.
Deep Medial Fields
Implicit representations of geometry, such as occupancy fields or signed distance fields (SDF), have recently re-gained popularity in encoding 3D solid shape in a functional form.
COTR: Correspondence Transformer for Matching Across Images
We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other.
Ranked #1 on
Dense Pixel Correspondence Estimation
on KITTI 2012
Dense Pixel Correspondence Estimation
Optical Flow Estimation
Canonical Capsules: Self-Supervised Capsules in Canonical Pose
We propose a self-supervised capsule architecture for 3D point clouds.
DeRF: Decomposed Radiance Fields
Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering.
Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems
In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network.
VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning
We show that our method can be applied to classification tasks on multiple different datasets -- including one that is a real-world dataset with heavy data imbalance -- significantly outperforming the state of the art.
Image Matching across Wide Baselines: From Paper to Practice
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric.
VoronoiNet: General Functional Approximators with Local Support
Voronoi diagrams are highly compact representations that are used in various Graphics applications.
Reducing the Human Effort in Developing PET-CT Registration
We aim to reduce the tedious nature of developing and evaluating methods for aligning PET-CT scans from multiple patient visits.
MIST: Multiple Instance Spatial Transformer Networks
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts.
Optimizing Through Learned Errors for Accurate Sports Field Registration
We propose an optimization-based framework to register sports field templates onto broadcast videos.
Beyond Cartesian Representations for Local Descriptors
We demonstrate that this representation is particularly amenable to learning descriptors with deep networks.
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds.
Linearized Multi-Sampling for Differentiable Image Transformation
We propose a novel image sampling method for differentiable image transformation in deep neural networks.
Self-Supervised Deep Active Accelerated MRI
The reconstruction network is trained to give the highest reconstruction quality, given the MCTS sampling pattern.
MIST: Multiple Instance Spatial Transformer Network
We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts.
Anomaly Detection In Surveillance Videos
Image Reconstruction
LF-Net: Learning Local Features from Images
We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision.
Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system.
Learning to Find Good Correspondences
We develop a deep architecture to learn to find good correspondences for wide-baseline stereo.
HandSeg: An Automatically Labeled Dataset for Hand Segmentation from Depth Images
We propose an automatic method for generating high-quality annotations for depth-based hand segmentation, and introduce a large-scale hand segmentation dataset.
LIFT: Learned Invariant Feature Transform
We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description.
A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images
We present a method that estimates in real-time and under challenging conditions the 3D pose of a known object.
Learning to Assign Orientations to Feature Points
We show how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point.
TILDE: A Temporally Invariant Learned DEtector
We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive.
