Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking

• URL: http://arxiv.org/abs/2606.30754v1
• Date: Mon, 29 Jun 2026 18:00:42 GMT
• Title: Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking
• Abstract summary: Camera-based 4D-POT is a promising paradigm for holistic scene understanding from multi-view imagery.<n>Recent mask-based pipelines achieve strong performance by propagating instance queries across frames.<n>We propose a streaming Gaussian encoder that maintains a persistent scene representation for 4D-POT.
• Score: 15.311099668839665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Camera-based 4D panoptic occupancy tracking (4D-POT) is a promising paradigm for holistic scene understanding from multi-view imagery, enabling joint reasoning about geometry, semantics, and object identities across time. Recent mask-based pipelines achieve strong performance by propagating instance queries across frames. However, their underlying volumetric representations are typically recomputed at each timestep, limiting geometric temporal consistency, particularly under occlusion and for static scene elements. To address this limitation, we propose a streaming Gaussian encoder that maintains a persistent volumetric scene representation for 4D-POT. Our method models the scene as a fixed-size set of latent Gaussian queries that are propagated via ego-motion compensation and refreshed under a confidence-guided budget constraint. Crucially, we shape Gaussian opacities through depth-based supervision to serve as proxy for visibility, enabling confidence to accumulate as a temporally aggregated measure of persistent scene support. Together with a warmup-based multi-frame training strategy, this yields representation-level temporal coherence beyond decoder-only tracking. Extensive experiments on Occ3D-extended nuScenes and Waymo establish a new state-of-the-art for camera-based 4D-POT, improving tracking consistency with negligible computational overhead while remaining fully compatible with existing mask-based pipelines. We provide code and models at https://sge.cs.uni-freiburg.de.

Related papers

• Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction [49.87425331212591]
  We present C4G, a feed-forward 4D reconstruction framework built upon a compact set of timestamp-conditioned learnable Gaussian query tokens.<n>C4G achieves strong novel-view synthesis performance using significantly fewer Gaussians and without requiring camera poses.
  arXiv  Detail & Related papers  (2026-05-29T17:57:41Z)
• GemDepth: Geometry-Embedded Features for 3D-Consistent Video Depth [12.866152238833104]
  Video depth estimation extends monocular prediction into the temporal domain to ensure coherence.<n>Current approaches, which primarily rely on temporal smoothing via Transformers, struggle to maintain strict 3D geometric consistency.<n>We propose GemDepth, a framework built on the insight that an explicit awareness of camera motion and global 3D structure is a prerequisite for 3D consistency.
  arXiv  Detail & Related papers  (2026-05-11T13:11:54Z)
• RetimeGS: Continuous-Time Reconstruction of 4D Gaussian Splatting [9.254380348086135]
  temporal retiming is crucial for applications such as slow-motion playback, temporal editing, and post-production.<n>Most existing 4D Gaussian Splatting (4DGS) methods overfit at discrete frame indices but struggle to represent continuous-time frames, leading to ghosting artifacts when interpolating between timestamps.<n>We propose RetimeGS, a simple yet effective 4DGS representation that explicitly defines the temporal behavior of the 3D Gaussian and achieves temporal aliasing.
  arXiv  Detail & Related papers  (2026-03-14T06:26:27Z)
• Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking [17.16370461224889]
  4Dtemporal tracking is crucial for the safe and reliable operation of robots in dynamic environments.<n>In this paper we present Latent Gaussian splatting for 4D panoptic occupancy tracking.<n>We make code available at https://lags.cs.uni-freiburg.de/.
  arXiv  Detail & Related papers  (2026-02-26T16:34:49Z)
• EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis [43.898895514609286]
  EvolSplat4D is a feed-forward framework that moves beyond existing per-pixel paradigms by unifying volume-based and pixel-based Gaussian prediction.<n>We show that EvolSplat4D reconstructs both static and dynamic environments with superior accuracy and consistency, outperforming both per-scene optimization and state-of-the-art feed-forward baselines.
  arXiv  Detail & Related papers  (2026-01-22T13:39:29Z)
• Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models [79.06910348413861]
  We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image.<n>Given a single input image, a camera trajectory, and an optional text prompt, Diff4Splat directly predicts a deformable 3D Gaussian field that encodes appearance, geometry, and motion.
  arXiv  Detail & Related papers  (2025-11-01T11:16:25Z)
• 4D Driving Scene Generation With Stereo Forcing [62.47705572424127]
  Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization.<n>We present PhiGenesis, a unified framework for 4D scene generation that extends video generation techniques with geometric and temporal consistency.
  arXiv  Detail & Related papers  (2025-09-24T15:37:17Z)
• Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency [49.875459658889355]
  Free4D is a tuning-free framework for 4D scene generation from a single image.<n>Our key insight is to distill pre-trained foundation models for consistent 4D scene representation.<n>The resulting 4D representation enables real-time, controllable rendering.
  arXiv  Detail & Related papers  (2025-03-26T17:59:44Z)
• Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving [116.10577967146762]
  We propose Driv3R, a framework that directly regresses per-frame point maps from multi-view image sequences.<n>We employ a 4D flow predictor to identify moving objects within the scene to direct our network focus more on reconstructing these dynamic regions.<n>Driv3R outperforms previous frameworks in 4D dynamic scene reconstruction, achieving 15x faster inference speed.
  arXiv  Detail & Related papers  (2024-12-09T18:58:03Z)
• 4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency [118.15258850780417]
  We present textbf4DGen, a novel framework for grounded 4D content creation.<n>Our pipeline facilitates controllable 4D generation, enabling users to specify the motion via monocular video or adopt image-to-video generations.<n>Compared to existing video-to-4D baselines, our approach yields superior results in faithfully reconstructing input signals.
  arXiv  Detail & Related papers  (2023-12-28T18:53:39Z)

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.