2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction

• URL: http://arxiv.org/abs/2603.19964v2
• Date: Mon, 23 Mar 2026 08:36:54 GMT
• Title: 2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction
• Abstract summary: 2K Retrofit is a novel framework that enables efficient 2K-resolution inference for any geometric foundation model.<n>Our approach leverages fast coarse predictions and an entropy-based sparse refinement selectively to enhance high-uncertainty regions.<n>Our experiments on widely used benchmark demonstrate that 2K Retrofit consistently achieves state-of-the-art accuracy and speed.
• Score: 38.02331315557929
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: High-resolution geometric prediction is essential for robust perception in autonomous driving, robotics, and AR/MR, but current foundation models are fundamentally limited by their scalability to real-world, high-resolution scenarios. Direct inference on 2K images with these models incurs prohibitive computational and memory demands, making practical deployment challenging. To tackle the issue, we present 2K Retrofit, a novel framework that enables efficient 2K-resolution inference for any geometric foundation model, without modifying or retraining the backbone. Our approach leverages fast coarse predictions and an entropy-based sparse refinement to selectively enhance high-uncertainty regions, achieving precise and high-fidelity 2K outputs with minimal overhead. Extensive experiments on widely used benchmark demonstrate that 2K Retrofit consistently achieves state-of-the-art accuracy and speed, bridging the gap between research advances and scalable deployment in high-resolution 3D vision applications. Code will be released upon acceptance.

Related papers

• L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction [45.197986759830314]
  This paper presents L2D2-GS, a unified framework that reformulates generalizable reconstruction not as a one-shot regression, but as a robust iterative process of optimization and densification.<n>Our method achieves state-of-the-art reconstruction fidelity and strong zero-shot generalization, while using fewer primitives than competing baselines.
  arXiv  Detail & Related papers  (2026-06-28T12:51:17Z)
• RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation [11.94699228168484]
  RaysUp is an ultra-lightweight, task-agnostic, and VFM-agnostic feature upsampling framework.<n>It reconstructs high-resolution feature maps at arbitrary dense generalizations.<n>Experiments demonstrate that RaysUp state-of-the-art performance while using only 16% of the parameters of AnyUp.
  arXiv  Detail & Related papers  (2026-06-22T01:37:56Z)
• LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows [10.300202521638274]
  We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows impacts feed-forward 3D reconstruction.<n>We show that expanding the context window -- by substantially increasing the number of active object and image tokens -- remarkably narrows this gap and enables high-fidelity 3D object reconstruction and inverse rendering.
  arXiv  Detail & Related papers  (2026-04-06T21:21:12Z)
• GauSSmart: Enhanced 3D Reconstruction through 2D Foundation Models and Geometric Filtering [50.675710727721786]
  We propose GauSSmart, a hybrid method that bridges 2D foundational models and 3D Gaussian Splatting reconstruction.<n>Our approach integrates established 2D computer vision techniques, including convex filtering and semantic feature supervision.<n>We validate our approach across three datasets, where GauSSmart consistently outperforms existing Gaussian Splatting.
  arXiv  Detail & Related papers  (2025-10-16T03:38:26Z)
• H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction [39.22287224290769]
  H3R is a hybrid framework that integrates latent fusion with attention-based feature aggregation.<n>By integrating both paradigms, our approach enhances generalization while converging 2$times$ faster than existing methods.<n>Our method supports variable-number and high-resolution input views while demonstrating robust cross-dataset generalization.
  arXiv  Detail & Related papers  (2025-08-05T05:56:30Z)
• Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention [54.15345846343084]
  We propose Ultra3D, an efficient 3D generation framework that significantly accelerates sparse voxel modeling without compromising quality.<n>Part Attention is a geometry-aware localized attention mechanism that restricts attention computation within semantically consistent part regions.<n>Experiments demonstrate that Ultra3D supports high-resolution 3D generation at 1024 resolution and achieves state-of-the-art performance in both visual fidelity and user preference.
  arXiv  Detail & Related papers  (2025-07-23T17:57:16Z)
• Ultra-Resolution Adaptation with Ease [62.56434979517156]
  We propose a set of key guidelines for ultra-resolution adaptation termed emphURAE.<n>We show that tuning minor components of the weight matrices outperforms widely-used low-rank adapters when synthetic data are unavailable.<n>Experiments validate that URAE achieves comparable 2K-generation performance to state-of-the-art closed-source models like FLUX1.1 [Pro] Ultra with only 3K samples and 2K iterations.
  arXiv  Detail & Related papers  (2025-03-20T16:44:43Z)
• GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
  Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.<n>We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.<n>GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
  arXiv  Detail & Related papers  (2024-12-12T17:59:03Z)
• UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues [55.69339788566899]
  UPose3D is a novel approach for multi-view 3D human pose estimation. It improves robustness and flexibility without requiring direct 3D annotations.
  arXiv  Detail & Related papers  (2024-04-23T00:18:00Z)
• Occlusion-Robust Object Pose Estimation with Holistic Representation [42.27081423489484]
  State-of-the-art (SOTA) object pose estimators take a two-stage approach. We develop a novel occlude-and-blackout batch augmentation technique. We also develop a multi-precision supervision architecture to encourage holistic pose representation learning.
  arXiv  Detail & Related papers  (2021-10-22T08:00:26Z)

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.