Neural Radiance Fields (NeRFs) have shown promise in applications like v...
While deep learning techniques have become extremely popular for solving...
Text-to-image diffusion models are now capable of generating images that...
Generating faithful visualizations of human faces requires capturing bot...
In this work, we introduce CC3D, a conditional generative model that
syn...
Neural radiance fields (NeRF) excel at synthesizing new views given
mult...
Camera pose estimation is a key step in standard 3D reconstruction pipel...
Traditional 3D scene understanding approaches rely on labeled 3D dataset...
This paper presents an end-to-end neural mapping method for camera
local...
We introduce a technique for pairwise registration of neural fields that...
Neural fields have rapidly been adopted for representing 3D signals, but...
We present 3DiM, a diffusion model for 3D novel view synthesis, which is...
Neural fields model signals by mapping coordinate inputs to sampled valu...
Neural Radiance Fields employ simple volume rendering as a way to overco...
Neural Radiance Fields (NeRFs) have demonstrated amazing ability to
synt...
We introduce a method for instance proposal generation for 3D point clou...
Given a monocular video, segmenting and decoupling dynamic objects while...
We present Panoptic Neural Fields (PNF), an object-aware neural scene
re...
We present Neural Descriptor Fields (NDFs), an object representation tha...
We extend neural 3D representations to allow for intuitive and interpret...
The goal of this work is to perform 3D reconstruction and novel view
syn...
We present NeSF, a method for producing 3D semantic fields from posed RG...
A classical problem in computer vision is to infer a 3D scene representa...
Neural Radiance Field (NeRF) is a popular method in data-driven 3D
recon...
We present a method for learning a generative 3D model based on neural
r...
Recently, huge strides were made in monocular and multi-view pose estima...
Implicit representations of geometry, such as occupancy fields or signed...
Invariance and equivariance to the rotation group have been widely discu...
We propose a novel framework for finding correspondences in images based...
We introduce a technique for 3D human keypoint estimation that directly
...
We propose an unsupervised capsule architecture for 3D point clouds. We
...
Capsule networks are designed to parse an image into a hierarchy of obje...
With the advent of Neural Radiance Fields (NeRF), neural networks can no...
In this technical report, we investigate extending convolutional neural
...
The medial axis transform has applications in numerous fields including
...
We present a generative model for stroke-based drawing tasks which is ab...
We present ShapeFlow, a flow-based model for learning a deformation spac...
We describe a novel approach for compressing truncated signed distance f...
In this technical report, we investigate efficient representations of
ar...
Voronoi diagrams are highly compact representations that are used in var...
Efficient representation of articulated objects such as human bodies is ...
Any solid object can be decomposed into a collection of convex polytopes...
Any solid object can be decomposed into a collection of convex polytopes...
Many problems in computer vision require dealing with sparse, unstructur...
We extend the formulation of position-based rods to include elastic
volu...
Volumetric (4D) performance capture is fundamental for AR/VR content
gen...
We propose a novel image sampling method for differentiable image
transf...
We propose a deep network that can be trained to tackle image reconstruc...
We introduce a large-scale RGBD hand segmentation dataset, with detailed...
There are many applications scenarios for which the computational perfor...