paper-with-me

홈 › Papers

Divide and Conquer: Rethinking the Training Paradigm of Neural Radiance Fields

2024-01-29 · Rongkai Ma, Leo Lebrat, Rodrigo Santa Cruz, Gil Avraham, Yan Zuo, Clinton Fookes, Olivier Salvado

Neural radiance fields (NeRFs) have exhibited potential in synthesizing high-fidelity views of 3D scenes but the standard training paradigm of NeRF presupposes an equal importance for each image in the training set. This assumption poses a significant challenge for rendering specific views presenting intricate geometries, thereby resulting in suboptimal performance. In this paper, we take a closer look at the implications of the current training paradigm and redesign this for more superior rendering quality by NeRFs. Dividing input views into multiple groups based on their visual similarities and training individual models on each of these groups enables each model to specialize on specific regions without sacrificing speed or efficiency. Subsequently, the knowledge of these specialized models is aggregated into a single entity via a teacher-student distillation paradigm, enabling spatial efficiency for online render-ing. Empirically, we evaluate our novel training framework on two publicly available datasets, namely NeRF synthetic and Tanks&Temples. Our evaluation demonstrates that our DaC training pipeline enhances the rendering quality of a state-of-the-art baseline model while exhibiting convergence to a superior minimum.

📄 PDF Abstract BibTeX arXiv:2401.16144

Code (0)

등록된 구현이 없습니다.

Tasks

NeRF

Methods 이 논문이 사용한 방법론

DAC 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

WDN: A Wide and Deep Network to Divide-and-Conquer Image Super-resolution

2020-10-07 · Vikram Singh, Anurag Mittal

Divide and conquer is an established algorithm design paradigm that has proven itself to solve a variety of problems efficiently. However, it is yet to be fully explored in solving problems with a neural network, particu…

Image Super-ResolutionSuper-Resolution

Transitive RL: Value Learning via Divide and Conquer

2025-10-26 · Seohong Park, Aditya Oberai, Pranav Atreya, Sergey Levine arxiv

In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditioned reinforcement learning (GCRL) problems…

Reinforcement Learning

Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding

2026-02-27 · Xiangzhong Luo, Yilin An, Zhicheng Yu, Weichen Liu 외 arxiv

Diffusion-based large language models (dLLMs) have shown promising performance across various reasoning tasks, establishing themselves as an alternative to autoregressive large language models (LLMs). Unlike autoregressi…

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

2021-03-25 · ICCV 2021 10 · Christian Reiser, Songyou Peng, Yiyi Liao, Andreas Geiger

NeRF synthesizes novel views of a scene with unprecedented quality by fitting a neural radiance field to RGB images. However, NeRF requires querying a deep Multi-Layer Perceptron (MLP) millions of times, leading to slow …

NeRF

Feature Interactions on Steroids: On the Composition of ML Models

2021-05-13 · Christian Kästner, Eunsuk Kang, Sven Apel

The lack of specifications is a key difference between traditional software engineering and machine learning. We discuss how it drastically impacts how we think about divide-and-conquer approaches to system design, and h…

BIG-bench Machine Learning