Related references
Note: Only part of the references are listed.
Article
Computer Science, Software Engineering
Thomas Mueller et al.
Summary: The research introduces a versatile new input encoding that allows for a reduction in the cost of training and evaluation by using a multiresolution hash table in neural networks.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Cheng Sun et al.
Summary: The study introduces a super-fast convergence approach for reconstructing the per-scene radiance field from a set of images with high quality in a short training time. This method outperforms traditional NeRF in terms of training time and quality.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Kangle Deng et al.
Summary: DS-NeRF is a method that learns radiance fields using depth supervision, allowing for better image rendering with fewer training views and faster training. It leverages structure-from-motion (SFM) and sparse 3D points as depth supervision, demonstrating the advantages of depth as a cheap and easily understandable supervisory signal. It is also compatible with other types of depth supervision.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Computer Science, Software Engineering
Lingjie Liu et al.
Summary: The Neural Actor method uses neural networks to learn pose-dependent geometric deformations and appearance effects from multi-view video input, and utilizes 2D texture maps on a body model to predict residual deformations and dynamic appearance, achieving high-quality synthesis of human actors.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Stephen Lombardi et al.
Summary: MVP combines the completeness of volumetric representations with the efficiency of primitive-based rendering, achieving spatially shared computation through a convolutional architecture and minimizing computation in empty regions of space by moving volumetric primitives to cover only occupied areas. Its parameterization supports correspondence and tracking constraints and is robust even in areas where classical tracking fails, producing superior results in terms of quality and runtime performance compared to state-of-the-art methods.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
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
Edgar Tretschk et al.
Summary: NR-NeRF is a reconstruction and novel view synthesis approach for non-rigid dynamic scenes, allowing sophisticated renderings to be generated from novel virtual camera views using a single consumer-grade camera, without explicit supervision during training, resulting in stable outcomes.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
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
Guy Gafni et al.
Summary: Dynamic neural radiance fields are introduced for modeling appearance and dynamics of a human face, utilizing an implicit representation based on scene representation networks and combining with a low-dimensional morphable model to handle facial dynamics. The volumetric representation allows for photorealistic image generation surpassing current video-based reenactment methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
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
Computer Science, Software Engineering
Stephen Lombardi et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)
Article
Computer Science, Software Engineering
Ben Mildenhall et al.
ACM TRANSACTIONS ON GRAPHICS
(2019)