VEON: Vocabulary-Enhanced Occupancy Prediction

• URL: http://arxiv.org/abs/2407.12294v1
• Date: Wed, 17 Jul 2024 03:26:50 GMT
• Title: VEON: Vocabulary-Enhanced Occupancy Prediction
• Abstract summary: We propose VEON for Vocabulary-Enhanced Occupancy predictioN by not only assembling but also adapting 2D foundation models. VEON achieves 15.14 mIoU on Occ3D-nuScenes, and shows the capability of recognizing objects with open-vocabulary categories.
• Score: 15.331332063879342
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Perceiving the world as 3D occupancy supports embodied agents to avoid collision with any types of obstacle. While open-vocabulary image understanding has prospered recently, how to bind the predicted 3D occupancy grids with open-world semantics still remains under-explored due to limited open-world annotations. Hence, instead of building our model from scratch, we try to blend 2D foundation models, specifically a depth model MiDaS and a semantic model CLIP, to lift the semantics to 3D space, thus fulfilling 3D occupancy. However, building upon these foundation models is not trivial. First, the MiDaS faces the depth ambiguity problem, i.e., it only produces relative depth but fails to estimate bin depth for feature lifting. Second, the CLIP image features lack high-resolution pixel-level information, which limits the 3D occupancy accuracy. Third, open vocabulary is often trapped by the long-tail problem. To address these issues, we propose VEON for Vocabulary-Enhanced Occupancy predictioN by not only assembling but also adapting these foundation models. We first equip MiDaS with a Zoedepth head and low-rank adaptation (LoRA) for relative-metric-bin depth transformation while reserving beneficial depth prior. Then, a lightweight side adaptor network is attached to the CLIP vision encoder to generate high-resolution features for fine-grained 3D occupancy prediction. Moreover, we design a class reweighting strategy to give priority to the tail classes. With only 46M trainable parameters and zero manual semantic labels, VEON achieves 15.14 mIoU on Occ3D-nuScenes, and shows the capability of recognizing objects with open-vocabulary categories, meaning that our VEON is label-efficient, parameter-efficient, and precise enough.

Related papers

• PandaPose: 3D Human Pose Lifting from a Single Image via Propagating 2D Pose Prior to 3D Anchor Space [62.10630827126755]
  PandaPose is a 3D human pose lifting approach via propagating 2D pose prior to 3D anchor space as the unified intermediate representation.<n>Our 3D anchor space comprises: (1) Joint-wise 3D anchors in the canonical coordinate system, providing accurate and robust priors to mitigate 2D pose estimation inaccuracies.
  arXiv  Detail & Related papers  (2026-02-01T08:20:40Z)
• Pursuing Minimal Sufficiency in Spatial Reasoning [42.564463357503875]
  spatial reasoning, ability to ground language in 3D understanding, remains a persistent challenge for Vision Models.<n>We identify two fundamental bottlenecks: inadequate 3D understanding capabilities stemming from 2D failures, and redundant 3D information.<n>We introduce MS ( spatial spatialer), a dual-agent framework that implements this principle.
  arXiv  Detail & Related papers  (2025-10-19T02:29:09Z)
• Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model [51.02616473941499]
  3D object segmentation with Large Language Models (LLMs) has become a prevailing paradigm due to its broad semantics, task flexibility, and strong generalization.<n>However, this paradigm is hindered by representation misalignment: LLMs process high-level semantic tokens, whereas 3D point clouds convey only dense geometric structures.<n>We present the Point Linguist Model (PLM), a general framework that bridges the representation gap between LLMs and dense 3D point clouds.
  arXiv  Detail & Related papers  (2025-09-09T15:01:28Z)
• Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding [8.090058633054852]
  We introduce a plug-and-play module that implicitly injects 3D geometry features into Vision-Language-Action (VLA) models.<n>Our method significantly improves the performance of state-of-the-art VLA models across diverse scenarios.
  arXiv  Detail & Related papers  (2025-07-01T04:05:47Z)
• Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding [58.38294408121273]
  We propose Cross-modal and Uncertainty-aware Agglomeration for Open-vocabulary 3D Scene Understanding dubbed CUA-O3D. Our method addresses two key challenges: (1) incorporating semantic priors from VLMs alongside the geometric knowledge of spatially-aware vision foundation models, and (2) using a novel deterministic uncertainty estimation to capture model-specific uncertainties.
  arXiv  Detail & Related papers  (2025-03-20T20:58:48Z)
• Learning A Zero-shot Occupancy Network from Vision Foundation Models via Self-supervised Adaptation [41.98740330990215]
  This work proposes a novel approach that bridges 2D vision foundation models with 3D tasks. We leverage the zero-shot capabilities of vision-language models for image semantics. We project the semantics into 3D space using the reconstructed metric depth, thereby providing 3D supervision.
  arXiv  Detail & Related papers  (2025-03-10T09:54:40Z)
• GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision [49.839374549646884]
  This paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone.
  arXiv  Detail & Related papers  (2024-05-17T07:31:20Z)
• Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction [10.698054425507475]
  This letter presents a novel multi-modal, i.e., LiDAR-camera 3D semantic occupancy prediction framework, dubbed Co-Occ. volume rendering in the feature space can proficiently bridge the gap between 3D LiDAR sweeps and 2D images.
  arXiv  Detail & Related papers  (2024-04-06T09:01:19Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data. We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
  We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
  arXiv  Detail & Related papers  (2023-11-03T15:41:15Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [114.47216525866435]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation. For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)
• Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding [57.47315482494805]
  Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is challenging because the model needs to both localize novel 3D objects and infer their semantic categories. We propose to harness pre-trained vision-language (VL) foundation models that encode extensive knowledge from image-text pairs to generate captions for 3D scenes.
  arXiv  Detail & Related papers  (2023-08-01T07:50:14Z)
• UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering [27.712689811093362]
  We present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track. Our solution achieves 51.27% mIoU on the official leaderboard with single model, placing 3rd in this challenge.
  arXiv  Detail & Related papers  (2023-06-15T13:23:57Z)
• Learning Occupancy for Monocular 3D Object Detection [25.56336546513198]
  We propose textbfOccupancyM3D, a method of learning occupancy for monocular 3D detection. It directly learns occupancy in frustum and 3D space, leading to more discriminative and informative 3D features and representations. Experiments on KITTI and open datasets demonstrate that the proposed method achieves a new state of the art and surpasses other methods by a significant margin.
  arXiv  Detail & Related papers  (2023-05-25T04:03:46Z)
• Weakly Supervised 3D Open-vocabulary Segmentation [104.07740741126119]
  We tackle the challenges in 3D open-vocabulary segmentation by exploiting pre-trained foundation models CLIP and DINO in a weakly supervised manner. We distill the open-vocabulary multimodal knowledge and object reasoning capability of CLIP and DINO into a neural radiance field (NeRF) A notable aspect of our approach is that it does not require any manual segmentation annotations for either the foundation models or the distillation process.
  arXiv  Detail & Related papers  (2023-05-23T14:16:49Z)
• CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP [19.66617835750012]
  Training a 3D scene understanding model requires complicated human annotations. vision-language pre-training models (e.g., CLIP) have shown remarkable open-world reasoning properties. We propose directly transferring CLIP's feature space to 3D scene understanding model without any form of supervision.
  arXiv  Detail & Related papers  (2023-03-08T17:30:58Z)
• 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior [50.73148041205675]
  The goal of the Semantic Scene Completion (SSC) task is to simultaneously predict a completed 3D voxel representation of volumetric occupancy and semantic labels of objects in the scene from a single-view observation. We propose to devise a new geometry-based strategy to embed depth information with low-resolution voxel representation. Our proposed geometric embedding works better than the depth feature learning from habitual SSC frameworks.
  arXiv  Detail & Related papers  (2020-03-31T09:33:46Z)

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.