Yusuke Sekikawa’s scientific contributions

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (1)


Fig. 1: Overview of Gumbel-NeRF. In the forward pass, a set of experts are processed to return densities and radiances. Out of N experts, only one expert with the highest density is selected. This maximum-pooling expert selection guarantees continuity in the final density field, like the original NeRF. Each expert is associated with an expert-specific latent code so that the expert learn to model a part of the object.
Fig. 3: Qualitative results of novel view synthesis of unseen objects using one-shot test-time optimization. Compared to CodeNeRF (CN) and Coded Switch-NeRF (CSN), our Gumbel-NeRF (GN-C) generally produces higher quality, especially for those parts marked by red boxes.
Fig. 4: Visualization of the decomposition provided by Coded Switch-NeRF (CSN) and Gumbel-NeRF (GN). Images in each column are rendered from only the 3D points handled by the corresponding expert.
Quantitative evaluation on ShapeNet-SRN cars test set. Note that we clip the rendered values to 0-1.
GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance Fields
  • Preprint
  • File available

October 2024

·

8 Reads

Yusuke Sekikawa

·

Chingwei Hsu

·

Satoshi Ikehata

·

[...]

·

Ikuro Sato

We propose Gumbel-NeRF, a mixture-of-expert (MoE) neural radiance fields (NeRF) model with a hindsight expert selection mechanism for synthesizing novel views of unseen objects. Previous studies have shown that the MoE structure provides high-quality representations of a given large-scale scene consisting of many objects. However, we observe that such a MoE NeRF model often produces low-quality representations in the vicinity of experts' boundaries when applied to the task of novel view synthesis of an unseen object from one/few-shot input. We find that this deterioration is primarily caused by the foresight expert selection mechanism, which may leave an unnatural discontinuity in the object shape near the experts' boundaries. Gumbel-NeRF adopts a hindsight expert selection mechanism, which guarantees continuity in the density field even near the experts' boundaries. Experiments using the SRN cars dataset demonstrate the superiority of Gumbel-NeRF over the baselines in terms of various image quality metrics.

Download