Transparent and specular object reconstruction
This state of the art report covers reconstruction methods for transparent and specular
objects or phenomena. While the 3D acquisition of opaque surfaces with Lambertian …
objects or phenomena. While the 3D acquisition of opaque surfaces with Lambertian …
Background-oriented schlieren imaging of supersonic aircraft in flight
JT Heineck, DW Banks, NT Smith, ET Schairer… - AIAA Journal, 2021 - arc.aiaa.org
This paper describes the development and use of background-oriented schlieren imaging of
a full-scale supersonic jet in flight. A series of flight tests was performed in April 2011 …
a full-scale supersonic jet in flight. A series of flight tests was performed in April 2011 …
Fluid simulation on neural flow maps
We introduce Neural Flow Maps, a novel simulation method bridging the emerging
paradigm of implicit neural representations with fluid simulation based on the theory of flow …
paradigm of implicit neural representations with fluid simulation based on the theory of flow …
Time-resolved 3d capture of non-stationary gas flows
Fluid simulation is one of the most active research areas in computer graphics. However, it
remains difficult to obtain measurements of real fluid flows for validation of the simulated …
remains difficult to obtain measurements of real fluid flows for validation of the simulated …
Single‐image tomography: 3D volumes from 2D cranial X‐rays
As many different 3D volumes could produce the same 2D x‐ray image, inverting this
process is challenging. We show that recent deep learning‐based convolutional neural …
process is challenging. We show that recent deep learning‐based convolutional neural …
Through the looking glass: Neural 3d reconstruction of transparent shapes
Recovering the 3D shape of transparent objects using a small number of unconstrained
natural images is an ill-posed problem. Complex light paths induced by refraction and …
natural images is an ill-posed problem. Complex light paths induced by refraction and …
A direct approach for instantaneous 3D density field reconstruction from background-oriented schlieren (BOS) measurements
We present a new numerical method for reconstruction of instantaneous density volume
from 3D background-oriented schlieren (3DBOS) measurements, with a validation on a …
from 3D background-oriented schlieren (3DBOS) measurements, with a validation on a …
Full 3D reconstruction of transparent objects
Numerous techniques have been proposed for reconstructing 3D models for opaque objects
in past decades. However, none of them can be directly applied to transparent objects. This …
in past decades. However, none of them can be directly applied to transparent objects. This …
Factorized motion fields for fast sparse input dynamic view synthesis
N Somraj, K Choudhary, SH Mupparaju… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
Designing a 3D representation of a dynamic scene for fast optimization and rendering is a
challenging task. While recent explicit representations enable fast learning and rendering of …
challenging task. While recent explicit representations enable fast learning and rendering of …
Scalarflow: a large-scale volumetric data set of real-world scalar transport flows for computer animation and machine learning
In this paper, we present ScalarFlow, a first large-scale data set of reconstructions of real-
world smoke plumes. In addition, we propose a framework for accurate physics-based …
world smoke plumes. In addition, we propose a framework for accurate physics-based …