paper-with-me

홈 › Papers

DyLiN: Making Light Field Networks Dynamic

2023-03-24 · CVPR 2023 1 · Heng Yu, Joel Julin, Zoltan A. Milacski, Koichiro Niinuma, Laszlo A. Jeni

Light Field Networks, the re-formulations of radiance fields to oriented rays, are magnitudes faster than their coordinate network counterparts, and provide higher fidelity with respect to representing 3D structures from 2D observations. They would be well suited for generic scene representation and manipulation, but suffer from one problem: they are limited to holistic and static scenes. In this paper, we propose the Dynamic Light Field Network (DyLiN) method that can handle non-rigid deformations, including topological changes. We learn a deformation field from input rays to canonical rays, and lift them into a higher dimensional space to handle discontinuities. We further introduce CoDyLiN, which augments DyLiN with controllable attribute inputs. We train both models via knowledge distillation from pretrained dynamic radiance fields. We evaluated DyLiN using both synthetic and real world datasets that include various non-rigid deformations. DyLiN qualitatively outperformed and quantitatively matched state-of-the-art methods in terms of visual fidelity, while being 25 - 71x computationally faster. We also tested CoDyLiN on attribute annotated data and it surpassed its teacher model. Project page: https://dylin2023.github.io .

📄 PDF Abstract BibTeX arXiv:2303.14243

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models

2026-03-30 · Nanxi Li, Xiang Wang, Yuanjie Chen, Haode Zhang 외 arxiv

While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in image and video understanding, their ability to comprehend the physical world has become an increasingly important research focu…

Advecting Scaffolds: Controlling The Remodelling Of Actomyosin With Anillin

2024-02-12 · Denni Currin-Ross, Sami C. Al-Izzi, Ivar Noordstra, Alpha S. Yap 외

We propose and analyse an active hydrodynamic theory that characterises the effects of the scaffold protein anillin. Anillin is found at major sites of cortical activity, such as adherens junctions and the cytokinetic fu…

Temporal receptive field in dynamic graph learning: A comprehensive analysis

2024-07-17 · Yannis Karmim, Leshanshui Yang, Raphaël Fournier S'Niehotta, Clément Chatelain 외

Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refer…

BenchmarkingDynamic Link PredictionGraph LearningLink Prediction+1

Investigation of HIV-1 Gag binding with RNAs and Lipids using Atomic Force Microscopy

2019-05-27

Atomic Force Microscopy was utilized to study the morphology of Gag, {\Psi}RNA, and their binding complexes with lipids in a solution environment with 0.1{\AA} vertical and 1nm lateral resolution. TARpolyA RNA was used a…

An Integrated Representation & Compression Scheme Based on Convolutional Autoencoders with 4D DCT Perceptual Encoding for High Dynamic Range Light Fields

2022-06-21 · Sally Khaidem, Mansi Sharma

The emerging and existing light field displays are highly capable of realistic presentation of 3D scenes on auto-stereoscopic glasses-free platforms. The light field size is a major drawback while utilising 3D displays a…