
-
Catching Out-of-Context Misinformation with Self-supervised Learning
Despite the recent attention to DeepFakes and other forms of image manip...
read it
-
SceneFormer: Indoor Scene Generation with Transformers
The task of indoor scene generation is to generate a sequence of objects...
read it
-
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
The rapid progress in 3D scene understanding has come with growing deman...
read it
-
Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences
Multi-object tracking from RGB-D video sequences is a challenging proble...
read it
-
Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos
We address the task of aligning CAD models to a video sequence of a comp...
read it
-
Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction
We present dynamic neural radiance fields for modeling the appearance an...
read it
-
ID-Reveal: Identity-aware DeepFake Video Detection
State-of-the-art DeepFake forgery detectors are trained in a supervised ...
read it
-
Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction
We introduce Neural Deformation Graphs for globally-consistent deformati...
read it
-
RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction
Semantic scene understanding from point clouds is particularly challengi...
read it
-
Face2Face: Real-time Face Capture and Reenactment of RGB Videos
We present Face2Face, a novel approach for real-time facial reenactment ...
read it
-
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
Neural rendering techniques promise efficient photo-realistic image synt...
read it
-
SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans
We present SPSG, a novel approach to generate high-quality, colored 3D m...
read it
-
Neural Non-Rigid Tracking
We introduce a novel, end-to-end learnable, differentiable non-rigid tra...
read it
-
Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
We propose Deep Distribution Transfer(DDT), a new transfer learning appr...
read it
-
State of the Art on Neural Rendering
Efficient rendering of photo-realistic virtual worlds is a long standing...
read it
-
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
We present 3D-MPA, a method for instance segmentation on 3D point clouds...
read it
-
SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans
We present a novel approach to reconstructing lightweight, CAD-based rep...
read it
-
Modeling 3D Shapes by Reinforcement Learning
We explore how to enable machines to model 3D shapes like human modelers...
read it
-
Local Implicit Grid Representations for 3D Scenes
Shape priors learned from data are commonly used to reconstruct 3D objec...
read it
-
Adversarial Texture Optimization from RGB-D Scans
Realistic color texture generation is an important step in RGB-D surface...
read it
-
ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
We introduce the new task of 3D object localization in RGB-D scans using...
read it
-
Neural Voice Puppetry: Audio-driven Facial Reenactment
We present Neural Voice Puppetry, a novel approach for audio-driven faci...
read it
-
DeepDeform: Learning Non-rigid RGB-D Reconstruction with Semi-supervised Data
Applying data-driven approaches to non-rigid 3D reconstruction has been ...
read it
-
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
We present a novel approach that converts partial and noisy RGB-D scans ...
read it
-
SpoC: Spoofing Camera Fingerprints
Thanks to the fast progress in synthetic media generation, creating real...
read it
-
ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation
We propose ViewAL, a novel active learning strategy for semantic segment...
read it
-
Joint Embedding of 3D Scan and CAD Objects
3D scan geometry and CAD models often contain complementary information ...
read it
-
RIO: 3D Object Instance Re-Localization in Changing Indoor Environments
In this work, we introduce the task of 3D object instance re-localizatio...
read it
-
Active Scene Understanding via Online Semantic Reconstruction
We propose a novel approach to robot-operated active understanding of un...
read it
-
End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans
We present a novel, end-to-end approach to align CAD models to an 3D sca...
read it
-
Deferred Neural Rendering: Image Synthesis using Neural Textures
The modern computer graphics pipeline can synthesize images at remarkabl...
read it
-
3D-SIC: 3D Semantic Instance Completion for RGB-D Scans
This paper focuses on the task of semantic instance completion: from an ...
read it
-
Inverse Path Tracing for Joint Material and Lighting Estimation
Modern computer vision algorithms have brought significant advancement t...
read it
-
Linear Inequality Constraints for Neural Network Activations
We propose a method to impose linear inequality constraints on neural ne...
read it
-
DDSL: Deep Differentiable Simplex Layer for Learning Geometric Signals
We present a Deep Differentiable Simplex Layer (DDSL) for neural network...
read it
-
FaceForensics++: Learning to Detect Manipulated Facial Images
The rapid progress in synthetic image generation and manipulation has no...
read it
-
NRMVS: Non-Rigid Multi-View Stereo
Scene reconstruction from unorganized RGB images is an important task in...
read it
-
Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation
Convolutional Neural Networks (CNN) have been successful in processing d...
read it
-
Spherical CNNs on Unstructured Grids
We present an efficient convolution kernel for Convolutional Neural Netw...
read it
-
RegNet: Learning the Optimization of Direct Image-to-Image Pose Registration
Direct image-to-image alignment that relies on the optimization of photo...
read it
-
3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
We introduce 3D-SIS, a novel neural network architecture for 3D semantic...
read it
-
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
Distinguishing fakes from real images is becoming increasingly difficult...
read it
-
DeepVoxels: Learning Persistent 3D Feature Embeddings
In this work, we address the lack of 3D understanding of generative neur...
read it
-
TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes
We introduce, TextureNet, a neural network architecture designed to extr...
read it
-
Scan2CAD: Learning CAD Model Alignment in RGB-D Scans
We present Scan2CAD, a novel data-driven method that learns to align cle...
read it
-
IGNOR: Image-guided Neural Object Rendering
We propose a new learning-based novel view synthesis approach for scanne...
read it
-
Scan2Mesh: From Unstructured Range Scans to 3D Meshes
We introduce Scan2Mesh, a novel data-driven generative approach which tr...
read it
-
Parsing Geometry Using Structure-Aware Shape Templates
Real-life man-made objects often exhibit strong and easily-identifiable ...
read it
-
HeadOn: Real-time Reenactment of Human Portrait Videos
We propose HeadOn, the first real-time source-to-target reenactment appr...
read it
-
Deep Video Portraits
We present a novel approach that enables photo-realistic re-animation of...
read it