
-
SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes
Neural implicit surface representations have emerged as a promising para...
read it
-
SMD-Nets: Stereo Mixture Density Networks
Despite stereo matching accuracy has greatly improved by deep learning i...
read it
-
CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields
Tremendous progress in deep generative models has led to photorealistic ...
read it
-
KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
NeRF synthesizes novel views of a scene with unprecedented quality by fi...
read it
-
Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
Impressive progress in 3D shape extraction led to representations that c...
read it
-
STEP: Segmenting and Tracking Every Pixel
In this paper, we tackle video panoptic segmentation, a task that requir...
read it
-
Counterfactual Generative Networks
Neural networks are prone to learning shortcuts – they often model simpl...
read it
-
GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields
Deep generative models allow for photorealistic image synthesis at high ...
read it
-
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. ...
read it
-
Category Level Object Pose Estimation via Neural Analysis-by-Synthesis
Many object pose estimation algorithms rely on the analysis-by-synthesis...
read it
-
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
While 2D generative adversarial networks have enabled high-resolution im...
read it
-
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
Neural rendering techniques promise efficient photo-realistic image synt...
read it
-
Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences
Perceiving the world in terms of objects is a crucial prerequisite for r...
read it
-
Learning Neural Light Transport
In recent years, deep generative models have gained significance due to ...
read it
-
Label Efficient Visual Abstractions for Autonomous Driving
It is well known that semantic segmentation can be used as an effective ...
read it
-
Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image
Humans perceive the 3D world as a set of distinct objects that are chara...
read it
-
Learning Implicit Surface Light Fields
Implicit representations of 3D objects have recently achieved impressive...
read it
-
Convolutional Occupancy Networks
Recently, implicit neural representations have gained popularity for lea...
read it
-
Self-Supervised Linear Motion Deblurring
Motion blurry images challenge many computer vision algorithms, e.g, fea...
read it
-
Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision
Learning-based 3D reconstruction methods have shown impressive results. ...
read it
-
Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis
In recent years, Generative Adversarial Networks have achieved impressiv...
read it
-
Attacking Optical Flow
Deep neural nets achieve state-of-the-art performance on the problem of ...
read it
-
Texture Fields: Learning Texture Representations in Function Space
In recent years, substantial progress has been achieved in learning-base...
read it
-
Robust Dense Mapping for Large-Scale Dynamic Environments
We present a stereo-based dense mapping algorithm for large-scale dynami...
read it
-
Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids
Abstracting complex 3D shapes with parsimonious part-based representatio...
read it
-
MOTS: Multi-Object Tracking and Segmentation
This paper extends the popular task of multi-object tracking to multi-ob...
read it
-
RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
In this paper, we consider the problem of reconstructing a dense 3D mode...
read it
-
Taking a Deeper Look at the Inverse Compositional Algorithm
In this paper, we provide a modern synthesis of the classic inverse comp...
read it
-
Occupancy Networks: Learning 3D Reconstruction in Function Space
With the advent of deep neural networks, learning-based approaches for 3...
read it
-
Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Cameras
We present a real-time dense geometric mapping algorithm for large-scale...
read it
-
Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System
Project AutoVision aims to develop localization and 3D scene perception ...
read it
-
Geometric Image Synthesis
The task of generating natural images from 3D scenes has been a long sta...
read it
-
Conditional Affordance Learning for Driving in Urban Environments
Most existing approaches to autonomous driving fall into one of two cate...
read it
-
PointFlowNet: Learning Representations for 3D Scene Flow Estimation from Point Clouds
Despite significant progress in image-based 3D scene flow estimation, th...
read it
-
Learning 3D Shape Completion under Weak Supervision
We address the problem of 3D shape completion from sparse and noisy poin...
read it
-
Which Training Methods for GANs do actually Converge?
Recent work has shown local convergence of GAN training for absolutely c...
read it
-
On the Integration of Optical Flow and Action Recognition
Most of the top performing action recognition methods use optical flow a...
read it
-
Semantic Visual Localization
Robust visual localization under a wide range of viewing conditions is a...
read it
-
Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes
The success of deep learning in computer vision is based on availability...
read it
-
OctNetFusion: Learning Depth Fusion from Data
In this paper, we present a learning based approach to depth fusion, i.e...
read it
-
Probabilistic Duality for Parallel Gibbs Sampling without Graph Coloring
We present a new notion of probabilistic duality for random variables in...
read it
-
OctNet: Learning Deep 3D Representations at High Resolutions
We present OctNet, a representation for deep learning with sparse 3D dat...
read it
-
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer
Semantic annotations are vital for training models for object recognitio...
read it
-
FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation
One of the most popular approaches to multi-target tracking is tracking-...
read it