Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

Article Computer Science, Software Engineering

Neural Radiosity

Saeed Hadadan et al.

Summary: The Neural Radiosity algorithm introduces the use of neural networks to represent the full four-dimensional radiance distribution, optimizing network parameters to minimize the norm of the residual in solving the rendering equation. This approach simplifies the implementation and allows for efficient synthesis of arbitrary views of a scene, with improved convergence compared to previous techniques.

ACM TRANSACTIONS ON GRAPHICS (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Acorn: Adaptive Coordinate Networks for Neural Scene Representation

Julien N. P. Martel et al.

Summary: Neural representations have emerged as a new paradigm in various applications, offering flexibility and accuracy at moderate resolutions but facing challenges in representing large-scale or complex scenes. A new hybrid implicit-explicit network architecture and training strategy has been introduced, showing promising results in fitting high-resolution images and 3D shapes while significantly reducing training times and memory requirements.

ACM TRANSACTIONS ON GRAPHICS (2021)

添加到收藏夹

Article Computer Science, Software Engineering

Real-time Neural Radiance Caching for Path Tracing

Thomas Muller et al.

Summary: The paper presents a real-time neural radiance caching method for path-traced global illumination, which is designed to handle fully dynamic scenes and achieve significant noise reduction while maintaining real-time performance. By utilizing adaptation training and self-training with simple iterative training updates, the method demonstrates state-of-the-art results on challenging scenarios without the need for pretraining.

ACM TRANSACTIONS ON GRAPHICS (2021)

添加到收藏夹

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)

添加到收藏夹

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)

添加到收藏夹

Article Computer Science, Software Engineering