Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation

• URL: http://arxiv.org/abs/2604.26454v1
• Date: Wed, 29 Apr 2026 09:11:36 GMT
• Title: Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation
• Abstract summary: Recent vision foundation models (VFMs) have significantly improved accuracy and generalization for dense prediction.<n>In this study, we present a systematic layer-wise analysis of DINOv3, revealing that 3D information is distributed non-uniformly.<n>Motivated by this, we introduce a Last-Layer-Centric Feature Recombination (LFR) module to enhance geometric expressiveness.
• Score: 4.654162664140336
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Monocular depth estimation (MDE) is a fundamental yet inherently ill-posed task. Recent vision foundation models (VFMs), particularly DINO-based transformers, have significantly improved accuracy and generalization for dense prediction. Prior works generally follow a unified paradigm: sampling a fixed set of intermediate transformer layers at uniform intervals to build multi-scale features. This common practice implicitly assumes that geometric information is uniformly distributed across layers, which may underutilize the structural 3D cues encoded in VFMs. In this study, we present a systematic layer-wise analysis of DINOv3, revealing that 3D information is distributed non-uniformly: deeper layers exhibit stronger depth predictability and better capture inter-sample geometric variation. Motivated by this, we introduce a Last-Layer-Centric Feature Recombination (LFR) module to enhance geometric expressiveness. LFR treats the final layer as a geometric anchor and adaptively selects complementary intermediate layers according to a minimal-similarity criterion. Selected features are fused with the last-layer representation via compact linear adapters.Extensive experiments show that LFR module consistently improves MDE accuracy and achieves state-of-the-art performance. Our analysis sheds light on how geometric knowledge is organized within VFMs and offers an efficient strategy for unlocking their potential in dense 3D tasks.

Related papers

• Multimodal Floorplan Encoding: Learning Dense Modality-Invariant Representations [7.719268720723826]
  We introduce the Multimodal Floorplan (MMFE), which maps diverse 2D indoor representations into a shared latent dense grid.<n> MMFE combines a frozen DINOv3 backbone with a trainable Dense Prediction Transformer (DPT) head, and is trained with a per-cell Information Noise-Contrastive Estimation (InfoNCE) objective.<n>On Structured3D, a held-out out-of-domain dataset, MMFE improves cross-modal dense matching, enables robust similarity alignment with RANSAC, and yields strong retrieval when paired with learned aggregation.
  arXiv  Detail & Related papers  (2026-09-11T11:21:09Z)
• Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs [13.627465963609936]
  GUIDE (Geometric Unrolling Inside MLLM Early-layers) is a progressive geometric priors injection framework.<n>We introduce a context-aware gating that enables the model to fetch requisite spatial cues based on current semantics.
  arXiv  Detail & Related papers  (2026-04-07T10:45:28Z)
• GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models [70.61152292499737]
  We argue that this gap does not arise from insufficient geometric priors, but from a misalignment in the training paradigm.<n>Existing approaches typically resort to naive feature concatenation and optimize directly for downstream tasks without geometry-specific supervision.<n>We propose GAP-MLLM, a Geometry-Aligned Pre-training paradigm that explicitly activates structural perception before downstream adaptation.
  arXiv  Detail & Related papers  (2026-03-17T12:43:48Z)
• MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts [50.37005070020306]
  MoRE is a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture.<n>MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation.<n>It integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction.
  arXiv  Detail & Related papers  (2025-10-31T06:54:27Z)
• Dens3R: A Foundation Model for 3D Geometry Prediction [44.13431776180547]
  Dens3R is a 3D foundation model designed for joint geometric dense prediction.<n>By integrating image-pair matching features with intrinsic invariance modeling, Dens3R accurately regresses multiple geometric quantities.
  arXiv  Detail & Related papers  (2025-07-22T07:22:30Z)
• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• Double-Shot 3D Shape Measurement with a Dual-Branch Network for Structured Light Projection Profilometry [14.749887303860717]
  We propose a dual-branch Convolutional Neural Network (CNN)-Transformer network (PDCNet) to process different structured light (SL) modalities.<n>Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images.<n>Our method can reduce fringe order ambiguity while producing high-accuracy results on self-made datasets.
  arXiv  Detail & Related papers  (2024-07-19T10:49:26Z)
• GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image [94.56927147492738]
  We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes from single images. We show that leveraging diffusion priors can markedly improve generalization, detail preservation, and efficiency in resource usage. We propose a simple yet effective strategy to segregate the complex data distribution of various scenes into distinct sub-distributions.
  arXiv  Detail & Related papers  (2024-03-18T17:50:41Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• Manifold Topology Divergence: a Framework for Comparing Data Manifolds [109.0784952256104]
  We develop a framework for comparing data manifold, aimed at the evaluation of deep generative models. Based on the Cross-Barcode, we introduce the Manifold Topology Divergence score (MTop-Divergence) We demonstrate that the MTop-Divergence accurately detects various degrees of mode-dropping, intra-mode collapse, mode invention, and image disturbance.
  arXiv  Detail & Related papers  (2021-06-08T00:30:43Z)

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.