3D-IDE: 3D Implicit Depth Emergent

• URL: http://arxiv.org/abs/2604.03296v1
• Date: Sat, 28 Mar 2026 00:54:19 GMT
• Title: 3D-IDE: 3D Implicit Depth Emergent
• Abstract summary: 3D-Implicit Depth Emergence is a method that reframes 3D perception as an emergent property derived from geometric self-vision.<n>Our method enables 3D perception to emerge implicitly, disentangling features in dense regions.<n>Our approach achieves a 55% reduction in inference latency while maintaining strong performance across diverse downstream tasks.
• Score: 45.72771473431863
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Leveraging 3D information within Multimodal Large Language Models (MLLMs) has recently shown significant advantages for indoor scene understanding. However, existing methods, including those using explicit ground-truth 3D positional encoding and those grafting external 3D foundation models for implicit geometry, struggle with the trade-off in 2D-3D representation fusion, leading to suboptimal deployment. To this end, we propose 3D-Implicit Depth Emergence, a method that reframes 3D perception as an emergent property derived from geometric self-supervision rather than explicit encoding. Our core insight is the Implicit Geometric Emergence Principle: by strategically leveraging privileged geometric supervision through mechanisms like a fine-grained geometry validator and global representation constraints, we construct an information bottleneck. This bottleneck forces the model to maximize the mutual information between visual features and 3D structures, allowing 3D awareness to emerge naturally within a unified visual representation. Unlike existing approaches, our method enables 3D perception to emerge implicitly, disentangling features in dense regions and, crucially, eliminating depth and pose dependencies during inference with zero latency overhead. This paradigm shift from external grafting to implicit emergence represents a fundamental rethinking of 3D knowledge integration in visual-language models. Extensive experiments demonstrate that our method surpasses SOTA on multiple 3D scene understanding benchmarks. Our approach achieves a 55% reduction in inference latency while maintaining strong performance across diverse downstream tasks, underscoring the effectiveness of meticulously designed auxiliary objectives for dependency-free 3D understanding. Source code can be found at github.com/ChushanZhang/3D-IDE.

Related papers

• Stream3Dv2: Geometric-Semantic Fusion Enhanced Streaming Zero-Shot 3D Scene Understanding [7.823301846592561]
  Stream3Dv2 is a training-free framework designed for robust streaming 3D perception.<n>We introduce a comprehensive geometric-semantic fusion mechanism that resolves geometric noise and semantic ambiguity.<n>Experiments on public datasets demonstrate that Stream3Dv2 consistently outperforms existing baselines in foundational open-vocabulary streaming 3D segmentation and detection.
  arXiv  Detail & Related papers  (2026-08-21T14:13:02Z)
• Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding [50.098085774845195]
  We propose a paradigm shift by leveraging the implicit spatial prior within large-scale generation models.<n>We introduce GeneEGA-3D (Video Extracted Generative Awareness), a plug-and-play framework that repurposes a pre-trained video diffusion model as a Latent World Simulator.
  arXiv  Detail & Related papers  (2026-03-19T17:59:58Z)
• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder [90.8453349494245]
  We present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space.<n>OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods.
  arXiv  Detail & Related papers  (2026-03-17T03:43:37Z)
• EA3D: Online Open-World 3D Object Extraction from Streaming Videos [55.48835711373918]
  We present ExtractAnything3D (EA3D), a unified online framework for open-world 3D object extraction.<n>Given a streaming video, EA3D dynamically interprets each frame using vision-language and 2D vision foundation encoders to extract object-level knowledge.<n>A recurrent joint optimization module directs the model's attention to regions of interest, simultaneously enhancing both geometric reconstruction and semantic understanding.
  arXiv  Detail & Related papers  (2025-10-29T03:56:41Z)
• 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation [17.294440057314812]
  Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks.<n>We propose Geometric Distillation, a framework that injects human-inspired geometric cues into pretrained VLMs.<n>Our method shapes representations to be geometry-aware while remaining compatible with natural image-text inputs.
  arXiv  Detail & Related papers  (2025-06-11T15:56:59Z)
• Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning [18.185457833299235]
  We propose a unified Instance-aware 3D Large Multi-modal Model (Inst3D-LMM) to deal with multiple 3D scene understanding tasks simultaneously.<n>We first introduce a novel Multi-view Cross-Modal Fusion (MCMF) module to inject the multi-view 2D semantics into their corresponding 3D geometric features.<n>For scene-level relation-aware tokens, we further present a 3D Instance Spatial Relation (3D-ISR) module to capture the intricate pairwise spatial relationships among objects.
  arXiv  Detail & Related papers  (2025-03-01T14:38:42Z)
• Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation [27.43973967994717]
  MT3D is a text-to-3D generative model that leverages a high-fidelity 3D object to overcome viewpoint bias.<n>By incorporating geometric details from a 3D asset, MT3D enables the creation of diverse and geometrically consistent objects.
  arXiv  Detail & Related papers  (2024-08-12T06:25:44Z)
• FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding [11.118857208538039]
  We present Foundation Model Embedded Gaussian Splatting (S), which incorporates vision-language embeddings of foundation models into 3D Gaussian Splatting (GS) Results demonstrate remarkable multi-view semantic consistency, facilitating diverse downstream tasks, beating state-of-the-art methods by 10.2 percent on open-vocabulary language-based object detection. This research explores the intersection of vision, language, and 3D scene representation, paving the way for enhanced scene understanding in uncontrolled real-world environments.
  arXiv  Detail & Related papers  (2024-01-03T20:39:02Z)
• Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior [52.44678180286886]
  2D diffusion models find a distillation approach that achieves excellent generalization and rich details without any 3D data. We propose Sherpa3D, a new text-to-3D framework that achieves high-fidelity, generalizability, and geometric consistency simultaneously.
  arXiv  Detail & Related papers  (2023-12-11T18:59:18Z)
• Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation [87.54570024320354]
  State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. We develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds.
  arXiv  Detail & Related papers  (2020-08-04T13:56:19Z)

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.