QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy

• URL: http://arxiv.org/abs/2511.17221v1
• Date: Fri, 21 Nov 2025 13:05:42 GMT
• Title: QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy
• Abstract summary: Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving.<n>Since large-scale 3D annotation is expensive, recent work explores self-supervised learning directly from sensor data without manual labels.<n>We introduce QueryOcc, a query-based self-supervised framework that learns continuous 3D occupancy directly through independent 4D semantic queries.
• Score: 9.514718375634345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving. Since large-scale 3D annotation is prohibitively expensive, recent work explores self-supervised learning directly from sensor data without manual labels. Existing approaches either rely on 2D rendering consistency, where 3D structure emerges only implicitly, or on discretized voxel grids from accumulated lidar point clouds, limiting spatial precision and scalability. We introduce QueryOcc, a query-based self-supervised framework that learns continuous 3D semantic occupancy directly through independent 4D spatio-temporal queries sampled across adjacent frames. The framework supports supervision from either pseudo-point clouds derived from vision foundation models or raw lidar data. To enable long-range supervision and reasoning under constant memory, we introduce a contractive scene representation that preserves near-field detail while smoothly compressing distant regions. QueryOcc surpasses previous camera-based methods by 26% in semantic RayIoU on the self-supervised Occ3D-nuScenes benchmark while running at 11.6 FPS, demonstrating that direct 4D query supervision enables strong self-supervised occupancy learning. https://research.zenseact.com/publications/queryocc/

Related papers

• Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding [34.1504914582344]
  3D Visual Grounding aims to localize objects in 3D scenes via natural language descriptions.<n>We propose "Think, Act, Build (TAB)", a generative 2D-to-3D reconstruction paradigm operating directly on raw RGB-D streams.<n>To overcome the multi-view coverage deficit caused by strict VLM semantic tracking, we introduce the Semantic-Anchored Geometric Expansion.
  arXiv  Detail & Related papers  (2026-04-01T06:12:16Z)
• E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models [78.1674905950243]
  We present the first comprehensive benchmark for 3D geometric foundation models (GFMs)<n>GFMs directly predict dense 3D representations in a single feed-forward pass, eliminating the need for slow or unavailable precomputed camera parameters.<n>We evaluate 16 state-of-the-art GFMs, revealing their strengths and limitations across tasks and domains.<n>All code, evaluation scripts, and processed data will be publicly released to accelerate research in 3D spatial intelligence.
  arXiv  Detail & Related papers  (2025-06-02T17:53:09Z)
• Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D [68.23391872643268]
  LOCATE 3D is a model for localizing objects in 3D scenes from referring expressions like "the small coffee table between the sofa and the lamp"<n>It operates directly on sensor observation streams (posed RGB-D frames), enabling real-world deployment on robots and AR devices.
  arXiv  Detail & Related papers  (2025-04-19T02:51:24Z)
• LangOcc: Self-Supervised Open Vocabulary Occupancy Estimation via Volume Rendering [0.5852077003870417]
  LangOcc is a novel approach for open vocabulary occupancy estimation. It is trained only via camera images, and can detect arbitrary semantics via vision-language alignment. We achieve state-of-the-art results in self-supervised semantic occupancy estimation on the Occ3D-nuScenes dataset.
  arXiv  Detail & Related papers  (2024-07-24T14:22:55Z)
• SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction [77.15924044466976]
  We propose SelfOcc to explore a self-supervised way to learn 3D occupancy using only video sequences. We first transform the images into the 3D space (e.g., bird's eye view) to obtain 3D representation of the scene. We can then render 2D images of previous and future frames as self-supervision signals to learn the 3D representations.
  arXiv  Detail & Related papers  (2023-11-21T17:59:14Z)
• Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving [34.368848580725576]
  We develop a label generation pipeline that produces dense, visibility-aware labels for any given scene. This pipeline comprises three stages: voxel densification, reasoning, and image-guided voxel refinement. We propose a new model, dubbed Coarse-to-Fine Occupancy (CTF-Occ) network, which demonstrates superior performance on the Occ3D benchmarks.
  arXiv  Detail & Related papers  (2023-04-27T17:40:08Z)
• 4D Unsupervised Object Discovery [53.561750858325915]
  We propose 4D unsupervised object discovery, jointly discovering objects from 4D data -- 3D point clouds and 2D RGB images with temporal information. We present the first practical approach for this task by proposing a ClusterNet on 3D point clouds, which is jointly optimized with a 2D localization network.
  arXiv  Detail & Related papers  (2022-10-10T16:05:53Z)
• 3D Object Detection with a Self-supervised Lidar Scene Flow Backbone [10.341296683155973]
  We propose using a self-supervised training strategy to learn a general point cloud backbone model for downstream 3D vision tasks. Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a 3D detection head. Experiments on KITTI and nuScenes benchmarks show that the proposed self-supervised pre-training increases 3D detection performance significantly.
  arXiv  Detail & Related papers  (2022-05-02T07:53:29Z)
• Unsupervised Learning of Visual 3D Keypoints for Control [104.92063943162896]
  Learning sensorimotor control policies from high-dimensional images crucially relies on the quality of the underlying visual representations. We propose a framework to learn such a 3D geometric structure directly from images in an end-to-end unsupervised manner. These discovered 3D keypoints tend to meaningfully capture robot joints as well as object movements in a consistent manner across both time and 3D space.
  arXiv  Detail & Related papers  (2021-06-14T17:59:59Z)
• Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds [4.518012967046983]
  Understanding the flow in 3D space of sparsely sampled points between two consecutive time frames is the core stone of modern geometric-driven systems. This work presents a new self-supervised training method and an architecture for the 3D scene flow estimation under occlusions.
  arXiv  Detail & Related papers  (2021-04-10T09:55:19Z)
• Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
  A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
  arXiv  Detail & Related papers  (2021-03-12T15:30:02Z)

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.