GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts

• URL: http://arxiv.org/abs/2405.18438v1
• Date: Mon, 8 Apr 2024 18:24:12 GMT
• Title: GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts
• Abstract summary: We propose a method that integrates an open vocabulary scene encoder into the architecture, establishing a robust connection between text and scene. Our methodology achieves up to a 30% reduction in the goal object distance metric compared to the prior state-of-the-art baseline model.
• Score: 48.28000728061778
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The connection between our 3D surroundings and the descriptive language that characterizes them would be well-suited for localizing and generating human motion in context but for one problem. The complexity introduced by multiple modalities makes capturing this connection challenging with a fixed set of descriptors. Specifically, closed vocabulary scene encoders, which require learning text-scene associations from scratch, have been favored in the literature, often resulting in inaccurate motion grounding. In this paper, we propose a method that integrates an open vocabulary scene encoder into the architecture, establishing a robust connection between text and scene. Our two-step approach starts with pretraining the scene encoder through knowledge distillation from an existing open vocabulary semantic image segmentation model, ensuring a shared text-scene feature space. Subsequently, the scene encoder is fine-tuned for conditional motion generation, incorporating two novel regularization losses that regress the category and size of the goal object. Our methodology achieves up to a 30% reduction in the goal object distance metric compared to the prior state-of-the-art baseline model on the HUMANISE dataset. This improvement is demonstrated through evaluations conducted using three implementations of our framework and a perceptual study. Additionally, our method is designed to seamlessly accommodate future 2D segmentation methods that provide per-pixel text-aligned features for distillation.

Related papers

• Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis [59.527737790821305]
  We propose a relationship-aware framework that uses 3D scene graphs to enhance open-vocabulary 3D understanding.<n>Our method constructs relational scene graphs from multi-view observations by leveraging vision-language reasoning to infer object relationships.<n>Experiments on ScanNetV2, ScanNet200, ScanNet$++$, and Replica demonstrate strong performance and generalization ability.
  arXiv  Detail & Related papers  (2026-07-06T17:29:49Z)
• Holo-Captioning: Toward the Text Equivalent of 3D Scenes [64.90901911061918]
  We formulate holo-captioning as generating a structured textual description that comprehensively depicts all entities within a 3D scene.<n>Building upon this foundation, we propose HoloScribe, a novel model that features an instance-aware decoupled pipeline for generating structured holo-captions.<n>We propose a comprehensive evaluation metric named HoloScore, and provide a human-curated test set to ensure reliable model assessment.
  arXiv  Detail & Related papers  (2026-07-03T03:14:17Z)
• ReLaGS: Relational Language Gaussian Splatting [20.136674901612334]
  We present a novel framework that constructs a hierarchical language-distilled Gaussian scene and its 3D semantic scene graph without scene-specific training.<n>On top of this hierarchy, we build an open-vocabulary 3D scene graph with Vision Language derived annotations and Graph Neural Network-based relational reasoning.<n>Our approach enables efficient and scalable open-vocabulary 3D reasoning by jointly modeling hierarchical semantics and inter/intra-object relationships.
  arXiv  Detail & Related papers  (2026-03-18T11:18:23Z)
• Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction [8.282478908772534]
  Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences.<n>Most existing methods use a dual-encoder framework that compresses motion and text into global embeddings.<n>We propose an interpretable, joint-angle-based motion representation that maps joint-level local features into a structured pseudo-image.
  arXiv  Detail & Related papers  (2026-03-10T17:26:42Z)
• SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion [74.70024991949269]
  We introduce SceneAdapt, a framework that injects scene awareness into text-conditioned motion models.<n>Key idea is to use motion inbetweening, learnable without text, as a proxy task to bridge two distinct datasets.<n>Results show that SceneAdapt effectively injects scene awareness into text-to-motion models.
  arXiv  Detail & Related papers  (2025-10-14T23:42:10Z)
• Holistic Understanding of 3D Scenes as Universal Scene Description [56.69740649781989]
  3D scene understanding is a long-standing challenge in computer vision and a key component in enabling mixed reality, wearable computing, and embodied AI. We introduce an expertly curated dataset in the Universal Scene Description (USD) format featuring high-quality manual annotations. With its broad and high-quality annotations, the data provides the basis for holistic 3D scene understanding models.
  arXiv  Detail & Related papers  (2024-12-02T11:33:55Z)
• See It All: Contextualized Late Aggregation for 3D Dense Captioning [38.14179122810755]
  3D dense captioning is a task to localize objects in a 3D scene and generate descriptive sentences for each object. Recent approaches in 3D dense captioning have adopted transformer encoder-decoder frameworks from object detection to build an end-to-end pipeline without hand-crafted components. We introduce SIA (See-It-All), a transformer pipeline that engages in 3D dense captioning with a novel paradigm called late aggregation.
  arXiv  Detail & Related papers  (2024-08-14T16:19:18Z)
• Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [57.232688209606515]
  We present HTCL, a novel Temporal Temporal Context Learning paradigm for improving camera-based semantic scene completion. Our method ranks $1st$ on the Semantic KITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU.
  arXiv  Detail & Related papers  (2024-07-02T09:11:17Z)
• Generating Human Interaction Motions in Scenes with Text Control [66.74298145999909]
  We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Our approach begins with pre-training a scene-agnostic text-to-motion diffusion model. To facilitate training, we embed annotated navigation and interaction motions within scenes.
  arXiv  Detail & Related papers  (2024-04-16T16:04:38Z)
• InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior [27.773451301040424]
  InstructScene is a novel generative framework that integrates a semantic graph prior and a layout decoder. We show that the proposed method surpasses existing state-of-the-art approaches by a large margin.
  arXiv  Detail & Related papers  (2024-02-07T10:09:00Z)
• Panoptic Vision-Language Feature Fields [27.209602602110916]
  We propose the first algorithm for open-vocabulary panoptic segmentation in 3D scenes. Our algorithm learns a semantic feature field of the scene by distilling vision-language features from a pretrained 2D model. Our method achieves panoptic segmentation performance similar to the state-of-the-art closed-set 3D systems on the HyperSim, ScanNet and Replica dataset.
  arXiv  Detail & Related papers  (2023-09-11T13:41:27Z)
• Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding [58.924180772480504]
  3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. We propose to leverage weakly supervised annotations to learn the 3D visual grounding model. We design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner.
  arXiv  Detail & Related papers  (2023-07-18T13:49:49Z)
• CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion [83.30168660888913]
  We present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model.
  arXiv  Detail & Related papers  (2023-05-25T17:39:13Z)
• Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language [4.86658723641864]
  We propose a novel text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural description. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions.
  arXiv  Detail & Related papers  (2023-05-25T08:32:41Z)
• Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation [90.74732705236336]
  Language-queried video actor segmentation aims to predict the pixel-mask of the actor which performs the actions described by a natural language query in the target frames. We propose a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoder over the target frame to accurately segment the queried actors.
  arXiv  Detail & Related papers  (2021-05-14T13:27:53Z)

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.