GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow

2025-02-24 · Simon Boeder, Fabian Gigengack, Benjamin Risse

Occupancy estimation has become a prominent task in 3D computer vision, particularly within the autonomous driving community. In this paper, we present a novel approach to occupancy estimation, termed GaussianFlowOcc, which is inspired by Gaussian Splatting and replaces traditional dense voxel grids with a sparse 3D Gaussian representation. Our efficient model architecture based on a Gaussian Transformer significantly reduces computational and memory requirements by eliminating the need for expensive 3D convolutions used with inefficient voxel-based representations that predominantly represent empty 3D spaces. GaussianFlowOcc effectively captures scene dynamics by estimating temporal flow for each Gaussian during the overall network training process, offering a straightforward solution to a complex problem that is often neglected by existing methods. Moreover, GaussianFlowOcc is designed for scalability, as it employs weak supervision and does not require costly dense 3D voxel annotations based on additional data (e.g., LiDAR). Through extensive experimentation, we demonstrate that GaussianFlowOcc significantly outperforms all previous methods for weakly supervised occupancy estimation on the nuScenes dataset while featuring an inference speed that is 50 times faster than current SOTA.

📄 PDF Abstract BibTeX arXiv:2502.17288

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Residual Connection 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation

2025-11-19 · Simon Boeder, Fabian Gigengack, Simon Roesler, Holger Caesar 외 arxiv

Recent progress in self- and weakly supervised occupancy estimation has largely relied on 2D projection or rendering-based supervision, which suffers from geometric inconsistencies and severe depth bleeding. We thus intr…

Scene Understanding

4D-ROLLS: 4D Radar Occupancy Learning via LiDAR Supervision

2025-05-20 · Ruihan Liu, Xiaoyi Wu, Xijun Chen, Liang Hu 외

A comprehensive understanding of 3D scenes is essential for autonomous vehicles (AVs), and among various perception tasks, occupancy estimation plays a central role by providing a general representation of drivable and o…

Autonomous Vehicles BEV Segmentation GPU

Predicting Vegetation Stratum Occupancy from Airborne LiDAR Data with Deep Learning

2022-01-20 · Ekaterina Kalinicheva, Loic Landrieu, Clément Mallet, Nesrine Chehata

We propose a new deep learning-based method for estimating the occupancy of vegetation strata from airborne 3D LiDAR point clouds. Our model predicts rasterized occupancy maps for three vegetation strata corresponding to…

Deep Learning regression

LetOccVote: Learning Weakly Supervised 3D Occupancy through Consensus

2026-09-04 · Chi Zhang, Qi Song, Feifei Li, Jie Li 외 arxiv

Weakly supervised 3D occupancy prediction reduces the reliance on costly 3D annotations by learning from 2D pseudo-labels generated by vision foundation models. However, existing methods typically use these imperfect pse…

FreeOcc: Training-free Panoptic Occupancy Prediction via Foundation Models

2026-03-06 · Andrew Caunes, Thierry Chateau, Vincent Fremont arxiv

Semantic and panoptic occupancy prediction for road scene analysis provides a dense 3D representation of the ego vehicle's surroundings. Current camera-only approaches typically rely on costly dense 3D supervision or req…