GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models

• URL: http://arxiv.org/abs/2501.01428v4
• Date: Tue, 11 Mar 2025 07:54:04 GMT
• Title: GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models
• Authors: Zhangyang Qi, Zhixiong Zhang, Ye Fang, Jiaqi Wang, Hengshuang Zhao,
• Abstract summary: 2D Vision-Language Models (VLMs) have made significant strides in image-text understanding tasks.<n>Recent advances have leveraged 3D point clouds and multi-view images as inputs, yielding promising results.<n>We propose a vision-based solution inspired by human perception, which merely relies on visual cues for 3D spatial understanding.
• Score: 39.488763757826426
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, 2D Vision-Language Models (VLMs) have made significant strides in image-text understanding tasks. However, their performance in 3D spatial comprehension, which is critical for embodied intelligence, remains limited. Recent advances have leveraged 3D point clouds and multi-view images as inputs, yielding promising results. However, we propose exploring a purely vision-based solution inspired by human perception, which merely relies on visual cues for 3D spatial understanding. This paper empirically investigates the limitations of VLMs in 3D spatial knowledge, revealing that their primary shortcoming lies in the lack of global-local correspondence between the scene and individual frames. To address this, we introduce GPT4Scene, a novel visual prompting paradigm in VLM training and inference that helps build the global-local relationship, significantly improving the 3D spatial understanding of indoor scenes. Specifically, GPT4Scene constructs a Bird's Eye View (BEV) image from the video and marks consistent object IDs across both frames and the BEV image. The model then inputs the concatenated BEV image and video frames with markers. In zero-shot evaluations, GPT4Scene improves performance over closed-source VLMs like GPT-4o. Additionally, we prepare a processed video dataset consisting of 165K text annotation to fine-tune open-source VLMs, achieving state-of-the-art performance on all 3D understanding tasks. Surprisingly, after training with the GPT4Scene paradigm, VLMs consistently improve during inference, even without object marker prompting and BEV image as explicit correspondence. It demonstrates that the proposed paradigm helps VLMs develop an intrinsic ability to understand 3D scenes, which paves the way for a seamless approach to extending pre-trained VLMs for 3D scene understanding.

Related papers

• NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation [14.046423852723615]
  We introduce a novel 3D Gaussian Splatting based hard visual prompting approach to generate diverse viewpoints around target objects. Our method simulates realistic 3D perspectives, effectively augmenting existing hard visual prompts. This training-free strategy integrates seamlessly with prior hard visual prompts, enriching object-descriptive features.
  arXiv  Detail & Related papers  (2025-04-20T14:39:27Z)
• Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness [73.72335146374543]
  We introduce reconstructive visual instruction tuning with 3D-awareness (Ross3D), which integrates 3D-aware visual supervision into the training procedure. Ross3D achieves state-of-the-art performance across various 3D scene understanding benchmarks.
  arXiv  Detail & Related papers  (2025-04-02T16:59:55Z)
• MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation [87.30919771444117]
  Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. Recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation. We introduce MLLM-For3D, a framework that transfers knowledge from 2D MLLMs to 3D scene understanding.
  arXiv  Detail & Related papers  (2025-03-23T16:40:20Z)
• 3D Scene Graph Guided Vision-Language Pre-training [11.131667398927394]
  3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions.<n>Existing approaches typically follow task-specific, highly specialized paradigms.<n>This paper proposes a 3D scene graph-guided vision-language pre-training framework.
  arXiv  Detail & Related papers  (2024-11-27T16:10:44Z)
• Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment [26.858034573776198]
  We propose a weakly supervised approach for 3D visual grounding based on Visual Linguistic Alignment. Our 3D-VLA exploits the superior ability of current large-scale vision-language models on aligning the semantics between texts and 2D images. During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images.
  arXiv  Detail & Related papers  (2023-12-15T09:08:14Z)
• Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training [51.632418297156605]
  We introduce MixCon3D, a method aiming to sculpt holistic 3D representation in contrastive language-image-3D pre-training. We develop the 3D object-level representation from complementary perspectives, e.g., multi-view rendered images with the point cloud. Then, MixCon3D performs language-3D contrastive learning, comprehensively depicting real-world 3D objects and bolstering text alignment.
  arXiv  Detail & Related papers  (2023-11-03T06:05:36Z)
• 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)
• CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data [80.42480679542697]
  We propose Contrastive Language-Image-Point Cloud Pretraining (CLIP$2$) to learn the transferable 3D point cloud representation in realistic scenarios. Specifically, we exploit naturally-existed correspondences in 2D and 3D scenarios, and build well-aligned and instance-based text-image-point proxies from those complex scenarios.
  arXiv  Detail & Related papers  (2023-03-22T09:32:45Z)
• PLA: Language-Driven Open-Vocabulary 3D Scene Understanding [57.47315482494805]
  Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space. Recent breakthrough of 2D open-vocabulary perception is driven by Internet-scale paired image-text data with rich vocabulary concepts. We propose to distill knowledge encoded in pre-trained vision-language (VL) foundation models through captioning multi-view images from 3D.
  arXiv  Detail & Related papers  (2022-11-29T15:52:22Z)

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.