Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields

• URL: http://arxiv.org/abs/2501.19084v1
• Date: Fri, 31 Jan 2025 12:19:14 GMT
• Title: Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields
• Authors: Xingyu Miao, Haoran Duan, Yang Bai, Tejal Shah, Jun Song, Yang Long, Rajiv Ranjan, Ling Shao,
• Abstract summary: We propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. To achieve this, we introduce an adapter module and mitigate the noise issue in the dense CLIP feature distillation process. Our method surpasses current state-of-the-art technologies in both training speed and performance.
• Score: 49.66011190843893
• License:
• Abstract: In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on multi-scale CLIP features and are limited by processing speed and storage requirements, our approach aims to streamline the workflow by directly and effectively distilling dense CLIP features, thereby achieving precise segmentation of 3D scenes using text. To achieve this, we introduce an adapter module and mitigate the noise issue in the dense CLIP feature distillation process through a self-cross-training strategy. Moreover, to enhance the accuracy of segmentation edges, this work presents a low-rank transient query attention mechanism. To ensure the consistency of segmentation for similar colors under different viewpoints, we convert the segmentation task into a classification task through label volume, which significantly improves the consistency of segmentation in color-similar areas. We also propose a simplified text augmentation strategy to alleviate the issue of ambiguity in the correspondence between CLIP features and text. Extensive experimental results show that our method surpasses current state-of-the-art technologies in both training speed and performance. Our code is available on: https://github.com/xingy038/Laser.git.

Related papers

• LiSD: An Efficient Multi-Task Learning Framework for LiDAR Segmentation and Detection [6.813145466843275]
  LiSD is a voxel-based encoder-decoder framework that addresses both segmentation and detection tasks. It achieves the state-of-the-art performance of 83.3% mIoU on the nuScenes segmentation benchmark for lidar-only methods.
  arXiv  Detail & Related papers  (2024-06-11T07:26:54Z)
• Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification [54.96876797812238]
  We present a novel CrOss-moDal nEighbor Representation(CODER) based on the distance structure between images and their neighbor texts. The key to construct a high-quality CODER lies in how to create a vast amount of high-quality and diverse texts to match with images. Experiment results across various datasets and models confirm CODER's effectiveness.
  arXiv  Detail & Related papers  (2024-04-27T02:04:36Z)
• Semantic Layering in Room Segmentation via LLMs [4.3154860982892425]
  SeLRoS is an advanced method for semantic room segmentation by integrating Large Language Models (LLMs) with traditional 2D map-based segmentation. We provide a novel framework that interprets and organizes complex information about each segmented area. The effectiveness of SeLRoS is verified through its application across 30 different 3D environments.
  arXiv  Detail & Related papers  (2024-03-19T17:23:44Z)
• Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition [77.93678598476149]
  We establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) By cascading the CLIP image encoder with the reversed CLIP text encoder, a symmetrical structure is built with an image-to-text feature flow. Extensive experiments demonstrate the effectiveness of CLIP-OCR with 93.8% average accuracy on six popular STR benchmarks.
  arXiv  Detail & Related papers  (2023-10-08T04:00:20Z)
• CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free [12.15899043709721]
  We propose an open-vocabulary semantic segmentation method, dubbed CLIP-DIY. It exploits CLIP classification abilities on patches of different sizes and aggregates the decision in a single map. We obtain state-of-the-art zero-shot semantic segmentation results on PASCAL VOC and perform on par with the best methods on COCO.
  arXiv  Detail & Related papers  (2023-09-25T16:52:59Z)
• [CLS] Token is All You Need for Zero-Shot Semantic Segmentation [60.06653755695356]
  We propose an embarrassingly simple yet highly effective zero-shot semantic segmentation (ZS3) method, based on the pre-trained vision-language model CLIP. Specifically, we use the [text] token output from the text branch, as an auxiliary semantic prompt, to replace the navigation [text] token in shallow layers of the ViT-based visual encoder. Our proposed ZS3 method achieves a SOTA performance, and it is even comparable with those few-shot semantic segmentation methods.
  arXiv  Detail & Related papers  (2023-04-13T01:35:07Z)
• CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation [56.58365347854647]
  We introduce a novel cost-based approach to adapt vision-language foundation models, notably CLIP. Our method potently adapts CLIP for segmenting seen and unseen classes by fine-tuning its encoders.
  arXiv  Detail & Related papers  (2023-03-21T12:28:21Z)
• CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation [19.208559353954833]
  This paper explores the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels. To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES.
  arXiv  Detail & Related papers  (2022-12-16T06:23:59Z)
• ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation [35.60888272729273]
  Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme. While effective, such a scheme requires two image encoders, one for proposal generation and one for CLIP, leading to a complicated pipeline and high computational cost. We propose a simpler-and-efficient one-stage solution that directly extends CLIP's zero-shot prediction capability from image to pixel level.
  arXiv  Detail & Related papers  (2022-12-07T12:05:00Z)
• Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation [88.49669148290306]
  We propose a novel weakly supervised multi-task framework called AuxSegNet to leverage saliency detection and multi-label image classification as auxiliary tasks. Inspired by their similar structured semantics, we also propose to learn a cross-task global pixel-level affinity map from the saliency and segmentation representations. The learned cross-task affinity can be used to refine saliency predictions and propagate CAM maps to provide improved pseudo labels for both tasks.
  arXiv  Detail & Related papers  (2021-07-25T11:39:58Z)

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.