3.8 Proceedings Paper

Block-NeRF: Scalable Large Scene Neural View Synthesis

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Software Engineering

Point-Based Neural Rendering with Per-View Optimization

T. Neff et al.

Summary: Recently, there has been a growing interest in neural rendering methods. This study introduces a general approach that utilizes MVS for initialization but allows further optimization of scene properties in the input view space, resulting in improved quality and speed in novel-view synthesis compared to previous methods.

COMPUTER GRAPHICS FORUM (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image

Andrew Liu et al.

Summary: The paper introduces the challenging problem of perpetual view generation, proposing a hybrid method that integrates geometry and image synthesis to generate long-range views based on a single image. By presenting a dataset and comparative experiments, it demonstrates the effectiveness of long-range generation compared to existing methods.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering

Bangbang Yang et al.

Summary: This paper presents a novel neural scene rendering system that learns an object-compositional neural radiance field for clustered and real-world scenes, providing realistic rendering with editing capability. The system features a two-pathway architecture for encoding scene geometry/appearance and individual object information, as well as a scene-guided training strategy for handling heavily cluttered scenes and learning sharp object boundaries. Extensive experiments demonstrate competitive performance in static scene novel-view synthesis and realistic rendering for object-level editing.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

FastNeRF: High-Fidelity Neural Rendering at 200FPS

Stephan J. Garbin et al.

Summary: This study introduces FastNeRF, the first NeRF-based system capable of rendering high-fidelity photorealistic images at 200Hz on a high-end consumer GPU. Through a graphics-inspired factorization, the method achieves compact caching of deep radiance maps and efficient querying, making it 3000 times faster than the original NeRF algorithm.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis

Pratul P. Srinivasan et al.

Summary: The method uses MLPs to parameterize a continuous volumetric function to represent scene properties, enabling the rendering of new views and performing well in complex lighting environments.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving

Yun Chen et al.

Summary: In this paper, a geometry-aware image composition process called GeoSim is proposed to synthesize novel urban driving scenarios by augmenting existing images with dynamic objects rendered at novel poses. The resulting synthetic images are realistic, traffic-aware, and geometrically consistent, allowing for applications in complex use cases. Two important applications demonstrated are long-range realistic video simulation across multiple camera sensors, and synthetic data generation for data augmentation on downstream segmentation tasks.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

Towaki Takikawa et al.

Summary: The study introduces an efficient neural representation that enables real-time rendering of high-fidelity neural SDFs and achieves state-of-the-art geometry reconstruction quality.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

Jonathan T. Barron et al.

Summary: Mip-NeRF is an extension of NeRF that reduces aliasing artifacts, improves fine detail representation, and is more efficient in speed and size compared to NeRF.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Article Robotics

Learning Robust Control Policies for End-to-End Autonomous Driving From Data-Driven Simulation

Alexander Amini et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Computer Science, Hardware & Architecture

Building Rome in a Day

Sameer Agarwal et al.

COMMUNICATIONS OF THE ACM (2011)

Article Computer Science, Artificial Intelligence

Detailed real-time urban 3D reconstruction from video

M. Pollefeys et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2008)

Article Computer Science, Artificial Intelligence

An automated method for large-scale, ground-based city model acquisition

C Früh et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2004)