State of the art on neural rendering

A Tewari, O Fried, J Thies, V Sitzmann… - Computer Graphics …, 2020 - Wiley Online Library
Efficient rendering of photo‐realistic virtual worlds is a long standing effort of computer
graphics. Modern graphics techniques have succeeded in synthesizing photo‐realistic …

Nerf: Representing scenes as neural radiance fields for view synthesis

B Mildenhall, PP Srinivasan, M Tancik… - Communications of the …, 2021 - dl.acm.org
We present a method that achieves state-of-the-art results for synthesizing novel views of
complex scenes by optimizing an underlying continuous volumetric scene function using a …

Nex: Real-time view synthesis with neural basis expansion

S Wizadwongsa, P Phongthawee… - Proceedings of the …, 2021 - openaccess.thecvf.com
We present NeX, a new approach to novel view synthesis based on enhancements of
multiplane image (MPI) that can reproduce next-level view-dependent effects--in real time …

Neural reflectance fields for appearance acquisition

S Bi, Z Xu, P Srinivasan, B Mildenhall… - arxiv preprint arxiv …, 2020 - arxiv.org
We present Neural Reflectance Fields, a novel deep scene representation that encodes
volume density, normal and reflectance properties at any 3D point in a scene using a fully …

Factor fields: A unified framework for neural fields and beyond

A Chen, Z Xu, X Wei, S Tang, H Su, A Geiger - arxiv preprint arxiv …, 2023 - arxiv.org
We present Factor Fields, a novel framework for modeling and representing signals. Factor
Fields decomposes a signal into a product of factors, each represented by a classical or …

Dictionary fields: Learning a neural basis decomposition

A Chen, Z Xu, X Wei, S Tang, H Su… - ACM Transactions on …, 2023 - dl.acm.org
We present Dictionary Fields, a novel neural representation which decomposes a signal into
a product of factors, each represented by a classical or neural field representation, operating …

[HTML][HTML] Deep appearance modeling: A survey

Y Dong - Visual Informatics, 2019 - Elsevier
Appearance modeling is an essential task in computer graphics for capturing and
reproducing rich appearance of real world materials under different lighting and viewing …

Real-time neural appearance models

T Zeltner*, F Rousselle*, A Weidlich*… - ACM Transactions on …, 2024 - dl.acm.org
We present a complete system for real-time rendering of scenes with complex appearance
previously reserved for offline use. This is achieved with a combination of algorithmic and …

[PDF][PDF] Neumip: Multi-resolution neural materials

A Kuznetsov - ACM Transactions on Graphics (ToG), 2021 - par.nsf.gov
The world is full of materials with interesting small-scale structure: a green pasture
consisting of millions of individual blades of grass, a scratched and partially rusted metallic …

CVAD-GAN: Constrained video anomaly detection via generative adversarial network

R Singh, A Sethi, K Saini, S Saurav, A Tiwari… - Image and Vision …, 2024 - Elsevier
Automatic detection of abnormal behavior in video sequences is a fundamental and
challenging problem for intelligent video surveillance systems. However, the existing state-of …