paper-with-me

Papers

Dynamic Fluid Surface Reconstruction Using Deep Neural Network

2020-06-01 · CVPR 2020 6 · Simron Thapa, Nianyi Li, Jinwei Ye

Recovering the dynamic fluid surface is a long-standing challenging problem in computer vision. Most existing image-based methods require multiple views or a dedicated imaging system. Here we present a learning-based single-image approach for 3D fluid surface reconstruction. Specifically, we design a deep neural network that estimates the depth and normal maps of a fluid surface by analyzing the refractive distortion of a reference background image. Due to the dynamic nature of fluid surfaces, our network uses recurrent layers that carry temporal information from previous frames to achieve spatio-temporally consistent reconstruction given a video input. Due to the lack of fluid data, we synthesize a large fluid dataset using physics-based fluid modeling and rendering techniques for network training and validation. Through experiments on simulated and real captured fluid images, we demonstrate that our proposed deep neural network trained on our fluid dataset can recover dynamic 3D fluid surfaces with high accuracy.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Surface Reconstruction

Similar Papers 제목 키워드 기반

Stereo-Based 3D Reconstruction of Dynamic Fluid Surfaces by Global Optimization

2017-07-01 · CVPR 2017 7 · Yiming Qian, Minglun Gong, Yee-Hong Yang

3D reconstruction of dynamic fluid surfaces is an open and challenging problem in computer vision. Unlike previous approaches that reconstruct each surface point independently and often return noisy depth maps, we propos…

3D geometry3D Reconstructionglobal-optimization

FluidGaussian: Propagating Simulation-Based Uncertainty Toward Functionally-Intelligent 3D Reconstruction

2026-03-22 · Yuqiu Liu, Jialin Song, Marissa Ramirez de Chanlatte, Rochishnu Chowdhury 외 arxiv

Real objects that inhabit the physical world follow physical laws and thus behave plausibly during interaction with other physical objects. However, current methods that perform 3D reconstructions of real-world scenes fr…

3D ReconstructionActive Learning

A GPU-based Hydrodynamic Simulator with Boid Interactions

2023-11-25 · Xi Liu, Gizem Kayar, Ken Perlin

We present a hydrodynamic simulation system using the GPU compute shaders of DirectX for simulating virtual agent behaviors and navigation inside a smoothed particle hydrodynamical (SPH) fluid environment with real-time …

GPUSurface Reconstruction

Fluid Dynamics Network: Topology-Agnostic 4D Reconstruction via Fluid Dynamics Priors

2023-03-17 · Daniele Baieri, Stefano Esposito, Filippo Maggioli, Emanuele Rodolà

Representing 3D surfaces as level sets of continuous functions over $\mathbb{R}^3$ is the common denominator of neural implicit representations, which recently enabled remarkable progress in geometric deep learning and c…

4D reconstruction

NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Implicit Representation

2022-03-08 · Ziyu Wang, Wei Yang, Junming Cao, Lan Xu 외

Existing neural reconstruction schemes such as Neural Radiance Field (NeRF) are largely focused on modeling opaque objects. We present a novel neural refractive field(NeReF) to recover wavefront of transparent fluids by …

global-optimizationNeRFSurface Reconstruction