VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling

TL;DR

VIBUS introduces a two-stage data-efficient 3D scene parsing framework that leverages self-supervised learning and uncertainty-spectrum modeling to reduce the need for extensive manual annotations, achieving state-of-the-art results.

Contribution

The paper proposes VIBUS, a novel framework combining viewpoint bottleneck self-supervised learning and uncertainty-spectrum based pseudo-labeling for efficient 3D scene parsing.

Findings

Achieves state-of-the-art results on ScanNet benchmark.

Both Viewpoint Bottleneck and uncertainty-spectrum modeling significantly improve performance.

Effective in reducing manual annotation requirements for 3D scene parsing.

Abstract

Recently, 3D scenes parsing with deep learning approaches has been a heating topic. However, current methods with fully-supervised models require manually annotated point-wise supervision which is extremely user-unfriendly and time-consuming to obtain. As such, training 3D scene parsing models with sparse supervision is an intriguing alternative. We term this task as data-efficient 3D scene parsing and propose an effective two-stage framework named VIBUS to resolve it by exploiting the enormous unlabeled points. In the first stage, we perform self-supervised representation learning on unlabeled points with the proposed Viewpoint Bottleneck loss function. The loss function is derived from an information bottleneck objective imposed on scenes under different viewpoints, making the process of representation learning free of degradation and sampling. In the second stage, pseudo labels are harvested from the sparse labels based on uncertainty-spectrum modeling. By combining data-driven uncertainty measures and 3D mesh spectrum measures (derived from normal directions and geodesic distances), a robust local affinity metric is obtained. Finite gamma/beta mixture models are used to decompose category-wise distributions of these measures, leading to automatic selection of thresholds. We evaluate VIBUS on the public benchmark ScanNet and achieve state-of-the-art results on both validation set and online test server. Ablation studies show that both Viewpoint Bottleneck and uncertainty-spectrum modeling bring significant improvements. Codes and models are publicly available at https://github.com/AIR-DISCOVER/VIBUS.