Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
13
result(s) for
"Marschner, Steve"
Sort by:
Weaving Objects
3D weaving is an industrial process for creating volumetric material through organized multiaxis interlacing of yarns. The overall complexity and rarity of 3D weaving have limited its market to aerospace and military applications. Current textile design software does not address the ease of iterating through physical trialing so necessary for designers to access this medium. This paper describes the development of a series of volumetric textile samples culminating in the creation of a fully formed shoe and the collaboration with computer scientists to develop a visualization tool that addresses the consumer accessory design opportunities for this medium.
Journal Article
Caliber: Camera Localization and Calibration Using Rigidity Constraints
This article presents a camera calibration system,
Caliber
, and the underlying pose estimation problem it solves, which we call sensor localization with rigidity (SL-R). SL-R is a constraint-satisfaction-like problem that finds a set of poses satisfying certain constraints. These constraints include not only relative pose constraints such as those found in SLAM and motion estimation problems, but also rigidity constraints: the notion of objects that are rigidly attached to each other so that their relative pose is fixed over time even if that pose is not known
a priori
. We show that SL-R is NP-hard, but give an inference-based algorithm that works well in practice. SL-R enables
Caliber
, a tool to calibrate systems of cameras connected by rigid or actuated links, using image observations and information about known motions of the system. The user provides a model of the system in the form of a kinematic tree, and
Caliber
uses our SL-R algorithm to generate an estimate for the rigidity constraints, then performs nonlinear optimization to produce a solution that is locally least-squares optimal in terms of reprojection error. In this way,
Caliber
is able to calibrate a variety of setups that would have previously required special-purpose code to calibrate. We demonstrate
Caliber
in a number of different scenarios using both synthetic and experimental data.
Journal Article
Leveraging 4D Golf Apparel Wear Simulation in Online Shopping: A Promising Approach to Minimizing the Carbon Footprint
As fashion e-commerce grows, the online return rates are running higher than ever before. Online customers buy the same product in multiple sizes or colors with the intention of returning what is not necessary as they are unable to have a tactile experience during their purchase. In terms of sustainability, returns have a huge negative impact on the environment, causing waste sent to landfills and carbon emissions. In the United States alone, over 15 million metric tons of carbon dioxide are annually emitted from transporting returned inventory. This study explored an innovative way to help reduce online returns due to fit and sizing issues using four-dimensional (4D) golf apparel wear simulation. The study observed how online customers reacted to an apparel wear simulation where they could see the body–clothing interactions, such as dynamic changes in the drape of a garment and cloth deformations caused by different body movements, with a focus on golf apparel. Female customers (n = 13) with experience playing golf and purchasing golf apparel online participated in randomized experiments where three different e-commerce demo websites embedded with simulations were shown. In-depth interviews were followed to collect qualitative data, and surveying was used to quantitatively assess the perceived usefulness of 4D golf apparel wear simulations. The findings of the study indicated that the wear simulation has the potential to help customers find the correct fit and size when shopping online. By exploring the idea of providing a more accurate representation of how apparel fits and interacts with the body, this study sheds light on the promising approach of leveraging 4D golf apparel wear simulations in online shopping to enhance sustainable fashion and potentially contribute to reducing the carbon footprint by minimizing returns.
Journal Article
HairFormer: Transformer-Based Dynamic Neural Hair Simulation
Simulating hair dynamics that generalize across arbitrary hairstyles, body shapes, and motions is a critical challenge. Our novel two-stage neural solution is the first to leverage Transformer-based architectures for such a broad generalization. We propose a Transformer-powered static network that predicts static draped shapes for any hairstyle, effectively resolving hair-body penetrations and preserving hair fidelity. Subsequently, a dynamic network with a novel cross-attention mechanism fuses static hair features with kinematic input to generate expressive dynamics and complex secondary motions. This dynamic network also allows for efficient fine-tuning of challenging motion sequences, such as abrupt head movements. Our method offers real-time inference for both static single-frame drapes and dynamic drapes over pose sequences. Our method demonstrates high-fidelity and generalizable dynamic hair across various styles, guided by physics-informed losses, and can resolve penetrations even for complex, unseen long hairstyles, highlighting its broad generalization.
Paper
Accurate Differential Operators for Hybrid Neural Fields
Neural fields have become widely used in various fields, from shape representation to neural rendering, and for solving partial differential equations (PDEs). With the advent of hybrid neural field representations like Instant NGP that leverage small MLPs and explicit representations, these models train quickly and can fit large scenes. Yet in many applications like rendering and simulation, hybrid neural fields can cause noticeable and unreasonable artifacts. This is because they do not yield accurate spatial derivatives needed for these downstream applications. In this work, we propose two ways to circumvent these challenges. Our first approach is a post hoc operator that uses local polynomial fitting to obtain more accurate derivatives from pre-trained hybrid neural fields. Additionally, we also propose a self-supervised fine-tuning approach that refines the hybrid neural field to yield accurate derivatives directly while preserving the initial signal. We show applications of our method to rendering, collision simulation, and solving PDEs. We observe that using our approach yields more accurate derivatives, reducing artifacts and leading to more accurate simulations in downstream applications.
Paper
A Simple Approach to Differentiable Rendering of SDFs
We present a simple algorithm for differentiable rendering of surfaces represented by Signed Distance Fields (SDF), which makes it easy to integrate rendering into gradient-based optimization pipelines. To tackle visibility-related derivatives that make rendering non-differentiable, existing physically based differentiable rendering methods often rely on elaborate guiding data structures or reparameterization with a global impact on variance. In this article, we investigate an alternative that embraces nonzero bias in exchange for low variance and architectural simplicity. Our method expands the lower-dimensional boundary integral into a thin band that is easy to sample when the underlying surface is represented by an SDF. We demonstrate the performance and robustness of our formulation in end-to-end inverse rendering tasks, where it obtains results that are competitive with or superior to existing work.
Paper
Rendering Participating Media Using Path Graphs
Rendering volumetric scattering media, including clouds, fog, smoke, and other complex materials, is crucial for realism in computer graphics. Traditional path tracing, while unbiased, requires many long path samples to converge in scenes with scattering media, and a lot of work is wasted by paths that make a negligible contribution to the image. Methods to make better use of the information learned during path tracing range from photon mapping to radiance caching, but struggle to support the full range of heterogeneous scattering media. This paper introduces a new volumetric rendering algorithm that extends and adapts the previous \\emph{path graph} surface rendering algorithm. Our method leverages the information collected through multiple-scattering transport paths to compute lower-noise estimates, increasing computational efficiency by reducing the required sample count. Our key contributions include an extended path graph for participating media and new aggregation and propagation operators for efficient path reuse in volumes. Compared to previous methods, our approach significantly boosts convergence in scenes with challenging volumetric light transport, including heterogeneous media with high scattering albedos and dense, forward-scattering translucent materials, under complex lighting conditions.
Paper
Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment
Novel View Synthesis (NVS) has traditionally relied on models with explicit 3D inductive biases combined with known camera parameters from Structure-from-Motion (SfM) beforehand. Recent vision foundation models like VGGT take an orthogonal approach -- 3D knowledge is gained implicitly through training data and loss objectives, enabling feed-forward prediction of both camera parameters and 3D representations directly from a set of uncalibrated images. While flexible, VGGT features lack explicit multi-view geometric consistency, and we find that improving such 3D feature consistency benefits both NVS and pose estimation tasks. We introduce Selfi, a self-improving 3D reconstruction pipeline via feature alignment, transforming a VGGT backbone into a high-fidelity 3D reconstruction engine by leveraging its own outputs as pseudo-ground-truth. Specifically, we train a lightweight feature adapter using a reprojection-based consistency loss, which distills VGGT outputs into a new geometrically-aligned feature space that captures spatial proximity in 3D. This enables state-of-the-art performance in both NVS and camera pose estimation, demonstrating that feature alignment is a highly beneficial step for downstream 3D reasoning.
Paper
Accurate Differential Operators for Hybrid Neural Fields
Neural fields have become widely used in various fields, from shape representation to neural rendering, and for solving partial differential equations (PDEs). With the advent of hybrid neural field representations like Instant NGP that leverage small MLPs and explicit representations, these models train quickly and can fit large scenes. Yet in many applications like rendering and simulation, hybrid neural fields can cause noticeable and unreasonable artifacts. This is because they do not yield accurate spatial derivatives needed for these downstream applications. In this work, we propose two ways to circumvent these challenges. Our first approach is a post hoc operator that uses local polynomial-fitting to obtain more accurate derivatives from pre-trained hybrid neural fields. Additionally, we also propose a self-supervised fine-tuning approach that refines the neural field to yield accurate derivatives directly while preserving the initial signal. We show the application of our method on rendering, collision simulation, and solving PDEs. We observe that using our approach yields more accurate derivatives, reducing artifacts and leading to more accurate simulations in downstream applications.
Paper