Papers
arxiv:2506.05563

VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction

Published on Jun 5
Authors:
,
,
,
,

Abstract

VoxelSplat enhances camera-based occupancy prediction by integrating 3D Gaussian Splatting for improved 3D semantics and scene flow learning through 2D projections and self-supervised motion modeling.

AI-generated summary

Recent advancements in camera-based occupancy prediction have focused on the simultaneous prediction of 3D semantics and scene flow, a task that presents significant challenges due to specific difficulties, e.g., occlusions and unbalanced dynamic environments. In this paper, we analyze these challenges and their underlying causes. To address them, we propose a novel regularization framework called VoxelSplat. This framework leverages recent developments in 3D Gaussian Splatting to enhance model performance in two key ways: (i) Enhanced Semantics Supervision through 2D Projection: During training, our method decodes sparse semantic 3D Gaussians from 3D representations and projects them onto the 2D camera view. This provides additional supervision signals in the camera-visible space, allowing 2D labels to improve the learning of 3D semantics. (ii) Scene Flow Learning: Our framework uses the predicted scene flow to model the motion of Gaussians, and is thus able to learn the scene flow of moving objects in a self-supervised manner using the labels of adjacent frames. Our method can be seamlessly integrated into various existing occupancy models, enhancing performance without increasing inference time. Extensive experiments on benchmark datasets demonstrate the effectiveness of VoxelSplat in improving the accuracy of both semantic occupancy and scene flow estimation. The project page and codes are available at https://zzy816.github.io/VoxelSplat-Demo/.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.05563 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.05563 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.05563 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.