OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation
- URL: http://arxiv.org/abs/2403.11796v2
- Date: Fri, 9 Aug 2024 09:00:21 GMT
- Title: OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation
- Authors: Haochen Jiang, Yueming Xu, Yihan Zeng, Hang Xu, Wei Zhang, Jianfeng Feng, Li Zhang,
- Abstract summary: Traditional 3D scene understanding approaches rely on expensive labeled 3D datasets to train a model for a single task with supervision.
We propose OpenOcc, a novel framework unifying the 3D scene reconstruction and open vocabulary understanding with neural radiance fields.
We show that our approach achieves competitive performance in 3D scene understanding tasks, especially for small and long-tail objects.
- Score: 30.76201018651464
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 3D reconstruction has been widely used in autonomous navigation fields of mobile robotics. However, the former research can only provide the basic geometry structure without the capability of open-world scene understanding, limiting advanced tasks like human interaction and visual navigation. Moreover, traditional 3D scene understanding approaches rely on expensive labeled 3D datasets to train a model for a single task with supervision. Thus, geometric reconstruction with zero-shot scene understanding i.e. Open vocabulary 3D Understanding and Reconstruction, is crucial for the future development of mobile robots. In this paper, we propose OpenOcc, a novel framework unifying the 3D scene reconstruction and open vocabulary understanding with neural radiance fields. We model the geometric structure of the scene with occupancy representation and distill the pre-trained open vocabulary model into a 3D language field via volume rendering for zero-shot inference. Furthermore, a novel semantic-aware confidence propagation (SCP) method has been proposed to relieve the issue of language field representation degeneracy caused by inconsistent measurements in distilled features. Experimental results show that our approach achieves competitive performance in 3D scene understanding tasks, especially for small and long-tail objects.
Related papers
- OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding [43.69535335079362]
Open-vocabulary 3D scene understanding (OV-3D) aims to localize and classify novel objects beyond the closed object classes.
Existing approaches and benchmarks primarily focus on the open vocabulary problem within the context of object classes.
We introduce a more challenging task called Generalized Open-Vocabulary 3D Scene Understanding (GOV-3D) to explore the open vocabulary problem beyond object classes.
arXiv Detail & Related papers (2024-08-20T17:31:48Z) - Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning [119.99066522299309]
KYN is a novel method for single-view scene reconstruction that reasons about semantic and spatial context to predict each point's density.
We show that KYN improves 3D shape recovery compared to predicting density for each 3D point in isolation.
We achieve state-of-the-art results in scene and object reconstruction on KITTI-360, and show improved zero-shot generalization compared to prior work.
arXiv Detail & Related papers (2024-04-04T17:59:59Z) - SUGAR: Pre-training 3D Visual Representations for Robotics [85.55534363501131]
We introduce a novel 3D pre-training framework for robotics named SUGAR.
SUGAR captures semantic, geometric and affordance properties of objects through 3D point clouds.
We show that SUGAR's 3D representation outperforms state-of-the-art 2D and 3D representations.
arXiv Detail & Related papers (2024-04-01T21:23:03Z) - POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images [32.33170182669095]
We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images.
The architecture consists of a 2D-3D encoder together with occupancy prediction and 3D-language heads.
The output is a dense voxel map of 3D grounded language embeddings enabling a range of open-vocabulary tasks.
arXiv Detail & Related papers (2024-01-17T18:51:53Z) - 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) - OpenScene: 3D Scene Understanding with Open Vocabularies [73.1411930820683]
Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision.
We propose OpenScene, an alternative approach where a model predicts dense features for 3D scene points that are co-embedded with text and image pixels in CLIP feature space.
This zero-shot approach enables task-agnostic training and open-vocabulary queries.
arXiv Detail & Related papers (2022-11-28T18:58:36Z) - Semantic Abstraction: Open-World 3D Scene Understanding from 2D
Vision-Language Models [17.606199768716532]
We study open-world 3D scene understanding, a family of tasks that require agents to reason about their 3D environment with an open-set vocabulary and out-of-domain visual inputs.
We propose Semantic Abstraction (SemAbs), a framework that equips 2D Vision-Language Models with new 3D spatial capabilities.
We demonstrate the usefulness of SemAbs on two open-world 3D scene understanding tasks.
arXiv Detail & Related papers (2022-07-23T13:10:25Z) - Object Scene Representation Transformer [56.40544849442227]
We introduce Object Scene Representation Transformer (OSRT), a 3D-centric model in which individual object representations naturally emerge through novel view synthesis.
OSRT scales to significantly more complex scenes with larger diversity of objects and backgrounds than existing methods.
It is multiple orders of magnitude faster at compositional rendering thanks to its light field parametrization and the novel Slot Mixer decoder.
arXiv Detail & Related papers (2022-06-14T15:40:47Z) - LanguageRefer: Spatial-Language Model for 3D Visual Grounding [72.7618059299306]
We develop a spatial-language model for a 3D visual grounding problem.
We show that our model performs competitively on visio-linguistic datasets proposed by ReferIt3D.
arXiv Detail & Related papers (2021-07-07T18:55:03Z)
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.