Search Results for author:
Found 9 papers, 2 papers with code
DISORF: A Distributed Online NeRF Training and Rendering Framework for Mobile Robots
We present a framework, DISORF, to enable online 3D reconstruction and visualization of scenes captured by resource-constrained mobile robots and edge devices.
GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting
Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined.
DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelines
In this work, we observe that the gradient computation phase during training is a significant bottleneck on GPUs due to the large number of atomic operations that need to be processed.
ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting
In this work, we introduce ENVIDR, a rendering and modeling framework for high-quality rendering and reconstruction of surfaces with challenging specular reflections.
Operator Fusion in XLA: Analysis and Evaluation
Machine learning (ML) compilers are an active area of research because they offer the potential to automatically speedup tensor programs.
SPIDR: SDF-based Neural Point Fields for Illumination and Deformation
To enable more accurate illumination updates after deformation, we use the shadow mapping technique to approximate the light visibility updates caused by geometry editing.
CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture
In this work, we aim to accelerate inference and training of coordinate-based MLPs for implicit neural representations by proposing a new split MLP architecture, CoordX.
A Simulation Platform for Multi-tenant Machine Learning Services on Thousands of GPUs
Multi-tenant machine learning services have become emerging data-intensive workloads in data centers with heavy usage of GPU resources.
Knowledge Consistency between Neural Networks and Beyond
As a generic tool, our method can be broadly used for different applications.
