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

• URL: http://arxiv.org/abs/2506.05563v1
• Date: Thu, 05 Jun 2025 20:19:35 GMT
• Title: VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction
• Authors: Ziyue Zhu, Shenlong Wang, Jin Xie, Jiang-jiang Liu, Jingdong Wang, Jian Yang,
• Abstract summary: Recent advancements in camera-based occupancy prediction have focused on the simultaneous prediction of 3D semantics and scene flow.<n>We propose a novel regularization framework called VoxelSplat to address these challenges and their underlying causes.<n>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.
• Score: 46.31516096522758
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/.

Related papers

• Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning [28.722572714606112]
  Flow3r is a framework that augments visual geometry learning with dense 2D correspondences (flow') as supervision.<n>Our key insight is that the flow prediction module should be factored: predicting flow between two images using geometry latents from one and pose latents from the other.
  arXiv  Detail & Related papers  (2026-02-23T18:59:30Z)
• Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware Distillation [10.159228582199924]
  Vision Foundation Models (VFMs) have achieved remarkable success when applied to various downstream 2D tasks.<n>Despite their effectiveness, they often exhibit a critical lack of 3D awareness.<n>We introduce Splat and Distill, a framework that instills robust 3D awareness into 2D VFMs by augmenting the teacher model with a fast, feed-forward 3D reconstruction pipeline.
  arXiv  Detail & Related papers  (2026-02-05T18:59:05Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding [54.859943475818234]
  We present Motion4D, a novel framework that integrates 2D priors from foundation models into a unified 4D Gaussian Splatting representation.<n>Our method features a two-part iterative optimization framework: 1) Sequential optimization, which updates motion and semantic fields in consecutive stages to maintain local consistency, and 2) Global optimization, which jointly refines all attributes for long-term coherence.<n>Our method significantly outperforms both 2D foundation models and existing 3D-based approaches across diverse scene understanding tasks, including point-based tracking, video object segmentation, and novel view synthesis.
  arXiv  Detail & Related papers  (2025-12-03T09:32:56Z)
• ODG: Occupancy Prediction Using Dual Gaussians [38.9869091446875]
  Occupancy prediction infers fine-grained 3D geometry and semantics from camera images of the surrounding environment.<n>Existing methods either adopt dense grids as scene representation, or learn the entire scene using a single set of sparse queries.<n>We present ODG, a hierarchical dual sparse Gaussian representation to effectively capture complex scene dynamics.
  arXiv  Detail & Related papers  (2025-06-11T06:03:03Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding [20.578106363482018]
  OpenGS-SLAM is an innovative framework that utilizes 3D Gaussian representation to perform dense semantic SLAM in open-set environments.<n>Our system integrates explicit semantic labels derived from 2D models into the 3D Gaussian framework, facilitating robust 3D object-level understanding.<n>Our method achieves 10 times faster semantic rendering and 2 times lower storage costs compared to existing methods.
  arXiv  Detail & Related papers  (2025-03-03T15:23:21Z)
• ManiTrend: Bridging Future Generation and Action Prediction with 3D Flow for Robotic Manipulation [11.233768932957771]
  3D flow represents the motion trend of 3D particles within a scene.<n>ManiTrend is a unified framework that models the dynamics of 3D particles, vision observations and manipulation actions.<n>Our method achieves state-of-the-art performance with high efficiency.
  arXiv  Detail & Related papers  (2025-02-14T09:13:57Z)
• GaussRender: Learning 3D Occupancy with Gaussian Rendering [86.89653628311565]
  GaussRender is a module that improves 3D occupancy learning by enforcing projective consistency.<n>Our method penalizes 3D configurations that produce inconsistent 2D projections, thereby enforcing a more coherent 3D structure.
  arXiv  Detail & Related papers  (2025-02-07T16:07:51Z)
• A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision [65.33043028101471]
  We introduce a diffusion model for Gaussian Splats, SplatDiffusion, to enable generation of three-dimensional structures from single images.<n>Existing methods rely on deterministic, feed-forward predictions, which limit their ability to handle the inherent ambiguity of 3D inference from 2D data.
  arXiv  Detail & Related papers  (2024-12-01T00:29:57Z)
• ALOcc: Adaptive Lifting-based 3D Semantic Occupancy and Cost Volume-based Flow Prediction [89.89610257714006]
  Existing methods prioritize higher accuracy to cater to the demands of these tasks. We introduce a series of targeted improvements for 3D semantic occupancy prediction and flow estimation. Our purelytemporalal architecture framework, named ALOcc, achieves an optimal tradeoff between speed and accuracy.
  arXiv  Detail & Related papers  (2024-11-12T11:32:56Z)
• 4D Contrastive Superflows are Dense 3D Representation Learners [62.433137130087445]
  We introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing pretraining objectives. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances alignment of the knowledge distilled from camera views.
  arXiv  Detail & Related papers  (2024-07-08T17:59:54Z)
• HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting [53.6394928681237]
  holistic understanding of urban scenes based on RGB images is a challenging yet important problem. Our main idea involves the joint optimization of geometry, appearance, semantics, and motion using a combination of static and dynamic 3D Gaussians. Our approach offers the ability to render new viewpoints in real-time, yielding 2D and 3D semantic information with high accuracy.
  arXiv  Detail & Related papers  (2024-03-19T13:39:05Z)
• OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flow [0.6577148087211809]
  We present a novel approach to occupancy estimation inspired by neural radiance field (NeRF) using only 2D labels. We employ differentiable volumetric rendering to predict depth and semantic maps and train a 3D network based on 2D supervision only.
  arXiv  Detail & Related papers  (2024-02-20T08:04:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.