MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes

02/23/2023
by   Christian Reiser, et al.
0

Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale to large scenes. We present a Memory-Efficient Radiance Field (MERF) representation that achieves real-time rendering of large-scale scenes in a browser. MERF reduces the memory consumption of prior sparse volumetric radiance fields using a combination of a sparse feature grid and high-resolution 2D feature planes. To support large-scale unbounded scenes, we introduce a novel contraction function that maps scene coordinates into a bounded volume while still allowing for efficient ray-box intersection. We design a lossless procedure for baking the parameterization used during training into a model that achieves real-time rendering while still preserving the photorealistic view synthesis quality of a volumetric radiance field.

READ FULL TEXT

page 1

page 9

page 10

research
08/08/2023

3D Gaussian Splatting for Real-Time Radiance Field Rendering

Radiance Field methods have recently revolutionized novel-view synthesis...
research
03/26/2021

Baking Neural Radiance Fields for Real-Time View Synthesis

Neural volumetric representations such as Neural Radiance Fields (NeRF) ...
research
01/05/2023

HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling

Volumetric scene representations enable photorealistic view synthesis fo...
research
12/15/2022

Real-Time Neural Light Field on Mobile Devices

Recent efforts in Neural Rendering Fields (NeRF) have shown impressive r...
research
09/02/2022

CLONeR: Camera-Lidar Fusion for Occupancy Grid-aided Neural Representations

Recent advances in neural radiance fields (NeRFs) achieve state-of-the-a...
research
10/15/2020

NeRF++: Analyzing and Improving Neural Radiance Fields

Neural Radiance Fields (NeRF) achieve impressive view synthesis results ...
research
03/22/2023

Balanced Spherical Grid for Egocentric View Synthesis

We present EgoNeRF, a practical solution to reconstruct large-scale real...

Please sign up or login with your details

Forgot password? Click here to reset