2022-08-18 更新
Progressive Multi-scale Light Field Networks
Authors:David Li, Amitabh Varshney
Neural representations have shown great promise in their ability to represent radiance and light fields while being very compact compared to the image set representation. However, current representations are not well suited for streaming as decoding can only be done at a single level of detail and requires downloading the entire neural network model. Furthermore, high-resolution light field networks can exhibit flickering and aliasing as neural networks are sampled without appropriate filtering. To resolve these issues, we present a progressive multi-scale light field network that encodes a light field with multiple levels of detail. Lower levels of detail are encoded using fewer neural network weights enabling progressive streaming and reducing rendering time. Our progressive multi-scale light field network addresses aliasing by encoding smaller anti-aliased representations at its lower levels of detail. Additionally, per-pixel level of detail enables our representation to support dithered transitions and foveated rendering.
PDF Accepted to 3DV 2022. Website at https://augmentariumlab.github.io/multiscale-lfn/
点此查看论文截图
DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images
Authors:Bing Wang, Lu Chen, Bo Yang
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an object field component to learn unique codes for all individual objects in 3D space only from 2D supervision. The key to this component is a series of carefully designed loss functions to enable every 3D point, especially in non-occupied space, to be effectively optimized even without 3D labels. In addition, we introduce an inverse query algorithm to freely manipulate any specified 3D object shape in the learned scene representation. Notably, our manipulation algorithm can explicitly tackle key issues such as object collisions and visual occlusions. Our method, called DM-NeRF, is among the first to simultaneously reconstruct, decompose, manipulate and render complex 3D scenes in a single pipeline. Extensive experiments on three datasets clearly show that our method can accurately decompose all 3D objects from 2D views, allowing any interested object to be freely manipulated in 3D space such as translation, rotation, size adjustment, and deformation.
PDF Our data and code are available at: https://github.com/vLAR-group/DM-NeRF
点此查看论文截图
Casual Indoor HDR Radiance Capture from Omnidirectional Images
Authors:Pulkit Gera, Mohammad Reza Karimi Dastjerdi, Charles Renaud, P. J. Narayanan, Jean-François Lalonde
We present PanoHDR-NeRF, a novel pipeline to casually capture a plausible full HDR radiance field of a large indoor scene without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, subsequently used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF pipeline can estimate full HDR panoramas from any location of the scene. Through experiments on a novel test dataset of a variety of real scenes with the ground truth HDR radiance captured at locations not seen during training, we show that PanoHDR-NeRF predicts plausible radiance from any scene point. We also show that the HDR images produced by PanoHDR-NeRF can synthesize correct lighting effects, enabling the augmentation of indoor scenes with synthetic objects that are lit correctly.
PDF
点此查看论文截图