DepthLM: Metric Depth From Vision Language Models

• URL: http://arxiv.org/abs/2509.25413v2
• Date: Wed, 01 Oct 2025 17:18:15 GMT
• Title: DepthLM: Metric Depth From Vision Language Models
• Abstract summary: Vision language models (VLMs) can flexibly address various vision tasks through text interactions.<n>We show that they can reach expert-level accuracy without architecture or loss change.<n>Our method DepthLM surpasses the accuracy of most advanced VLMs by over 2x.
• Score: 31.109287887180404
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision language models (VLMs) can flexibly address various vision tasks through text interactions. Although successful in semantic understanding, state-of-the-art VLMs including GPT-5 still struggle in understanding 3D from 2D inputs. On the other hand, expert pure vision models achieve super-human accuracy in metric depth estimation, a key 3D understanding task. However, they require task-specific architectures and losses. Such difference motivates us to ask: Can VLMs reach expert-level accuracy without architecture or loss change? We take per-pixel metric depth estimation as the representative task and show that the answer is yes! Surprisingly, comprehensive analysis shows that text-based supervised-finetuning with sparse labels is sufficient for VLMs to unlock strong 3D understanding, no dense prediction head or complex regression/regularization loss is needed. The bottleneck for VLMs lies actually in pixel reference and cross-dataset camera ambiguity, which we address through visual prompting and intrinsic-conditioned augmentation. With much smaller models, our method DepthLM surpasses the accuracy of most advanced VLMs by over 2x, making VLMs for the first time comparable with pure vision models. Interestingly, without explicit enforcement during training, VLMs trained with DepthLM naturally avoids over-smoothing, having much fewer flying points at boundary regions than pure vision models. The simplicity of DepthLM also enables a single VLM to cover various 3D tasks beyond metric depth. Our code and model will be released at the link below.

Related papers

• VLM3: Vision Language Models Are Native 3D Learners [36.094607074816814]
  Vision Language Models (VLMs) enable a unified model to solve various vision tasks through prompting.<n>We show that 3D understanding still largely relies on expert vision models with complex task-specific designs.<n>We propose VLM3, a scalable method with the simplest design that enables standard VLMs to master diverse 3D tasks.
  arXiv  Detail & Related papers  (2026-05-28T20:48:55Z)
• Unlocking Dense Metric Depth Estimation in VLMs [36.431792667223796]
  Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding.<n>We propose DepthVLM, a simple yet effective framework that transforms a single VLM into a native dense geometry predictor.<n>By attaching a lightweight depth head to the LLM backbone, DepthVLM generates full-resolution depth maps alongside language outputs in a single forward pass.
  arXiv  Detail & Related papers  (2026-05-15T11:54:17Z)
• View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs [19.27758108925572]
  3D visual grounding identifies objects in 3D scenes from language descriptions.<n>Existing zero-shot approaches leverage 2D vision-language models (VLMs) by converting 3D spatial information (SI) into forms to VLM processing.<n>We propose a new VLM x SI paradigm that externalizes the 3D SI into a form enabling the VLM to incrementally retrieve only what it needs during reasoning.
  arXiv  Detail & Related papers  (2025-12-10T00:59:17Z)
• Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens [54.18057944158818]
  Chain-of-Visual-Thought (COVT) is a framework that enables Vision-Language Models (VLMs) to reason through continuous visual tokens.<n>Within a small budget of roughly 20 tokens, COVT distills knowledge from lightweight vision experts.<n>During training, the VLM with COVT autoregressively predicts visual tokens to reconstruct dense supervision signals.
  arXiv  Detail & Related papers  (2025-11-24T18:55:19Z)
• Abstract 3D Perception for Spatial Intelligence in Vision-Language Models [100.13033631690114]
  Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding.<n>We introduce SandboxVLM, a framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM.<n>Our approach consistently improves spatial intelligence, achieving an 8.3% gain on SAT Real compared with baseline methods.
  arXiv  Detail & Related papers  (2025-11-14T04:16:09Z)
• Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding [11.222744122842023]
  We introduce a plug-and-play module that implicitly incorporates 3D geometry features into Vision-Language-Action (VLA) models.<n>Our method significantly improves the performance of state-of-the-art VLA models across diverse scenarios.
  arXiv  Detail & Related papers  (2025-07-01T04:05:47Z)
• Hidden in plain sight: VLMs overlook their visual representations [48.83628674170634]
  We compare vision language models (VLMs) to their visual encoders to understand their ability to integrate across these modalities.<n>We find that VLMs perform substantially worse than their visual encoders, dropping to near-chance performance.
  arXiv  Detail & Related papers  (2025-06-09T17:59:54Z)
• Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs [72.11701578308804]
  This paper categorizes recent 3D Vision-Language Models into 3D object-centric, 2D image-based, and 3D scene-centric approaches.<n>Despite the architectural similarity of 3D scene-centric VLMs to their 2D counterparts, they have exhibited comparatively lower performance compared with the latest 3D object-centric and 2D image-based approaches.<n>Our investigation suggests that while these models possess cross-modal alignment capabilities, they tend to over-rely on linguistic cues and overfit to frequent answer distributions.
  arXiv  Detail & Related papers  (2025-06-05T17:56:12Z)
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction [86.82819259860186]
  We introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning.<n>VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding.
  arXiv  Detail & Related papers  (2025-05-26T17:56:30Z)
• MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs [19.70116190496693]
  Multimodal large language models (MLLMs) excel at 2D visual understanding but remain limited in their ability to reason about 3D space.<n>In this work, we leverage large-scale high-quality 3D scene data with open-set annotations to introduce 1) a novel supervised fine-tuning dataset and 2) a new evaluation benchmark, focused on indoor scenes.
  arXiv  Detail & Related papers  (2025-03-17T12:34:22Z)
• GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models [39.488763757826426]
  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.
  arXiv  Detail & Related papers  (2025-01-02T18:59:59Z)
• How Well Can Vision Language Models See Image Details? [53.036922527685064]
  We introduce a pixel value prediction task to explore "How Well Can Vision Language Models See Image Details?" Our research reveals that incorporating pixel value prediction as one of the VLM pre-training tasks and vision encoder adaptation markedly boosts VLM performance on downstream image-language understanding tasks.
  arXiv  Detail & Related papers  (2024-08-07T17:59:40Z)

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.