Neural Rendering

Neural rendering studies how to represent scenes and light so computers can synthesize images from new viewpoints, times, or lighting conditions. Neural Radiance Fields (NeRFs) use implicit networks and differentiable volume rendering, while 3D Gaussian Splatting and other explicit primitives use rasterization or ray tracing; feed-forward and generative models aim to make reconstruction and rendering faster. Applications include dynamic scenes, avatars, relighting, neural materials, and sensor simulation, with quality often tested on benchmarks such as Mip-NeRF 360, LLFF, and DTU. A central challenge is balancing visual fidelity and geometric accuracy with speed, memory use, and reliable control of appearance under unseen views or lighting.