paper-with-me

홈 › Papers

PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

2023-12-04 · CVPR 2024 1 · Zhenyu Li, Shariq Farooq Bhat, Peter Wonka

Single image depth estimation is a foundational task in computer vision and generative modeling. However, prevailing depth estimation models grapple with accommodating the increasing resolutions commonplace in today's consumer cameras and devices. Existing high-resolution strategies show promise, but they often face limitations, ranging from error propagation to the loss of high-frequency details. We present PatchFusion, a novel tile-based framework with three key components to improve the current state of the art: (1) A patch-wise fusion network that fuses a globally-consistent coarse prediction with finer, inconsistent tiled predictions via high-level feature guidance, (2) A Global-to-Local (G2L) module that adds vital context to the fusion network, discarding the need for patch selection heuristics, and (3) A Consistency-Aware Training (CAT) and Inference (CAI) approach, emphasizing patch overlap consistency and thereby eradicating the necessity for post-processing. Experiments on UnrealStereo4K, MVS-Synth, and Middleburry 2014 demonstrate that our framework can generate high-resolution depth maps with intricate details. PatchFusion is independent of the base model for depth estimation. Notably, our framework built on top of SOTA ZoeDepth brings improvements for a total of 17.3% and 29.4% in terms of the root mean squared error (RMSE) on UnrealStereo4K and MVS-Synth, respectively.

📄 PDF Abstract BibTeX arXiv:2312.02284

Code (1)

zhyever/PatchFusion 공식 구현 pytorch

Tasks

Depth Estimation

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Monocular Reconstruction of Neural Tactile Fields

2026-02-13 · Pavan Mantripragada, Siddhanth Deshmukh, Eadom Dessalene, Manas Desai 외 arxiv

Robots operating in the real world must plan through environments that deform, yield, and reconfigure under contact, requiring interaction-aware 3D representations that extend beyond static geometric occupancy. To addres…

3D Reconstruction

Monocular Depth Estimation for Soft Visuotactile Sensors

2021-01-05 · Rares Ambrus, Vitor Guizilini, Naveen Kuppuswamy, Andrew Beaulieu 외

Fluid-filled soft visuotactile sensors such as the Soft-bubbles alleviate key challenges for robust manipulation, as they enable reliable grasps along with the ability to obtain high-resolution sensory feedback on contac…

Depth EstimationMonocular Depth Estimation

FlowFeat: Pixel-Dense Embedding of Motion Profiles

2025-11-10 · Nikita Araslanov, Anna Sonnweber, Daniel Cremers arxiv

Dense and versatile image representations underpin the success of virtually all computer vision applications. However, state-of-the-art networks, such as transformers, produce low-resolution feature grids, which are subo…

Monocular Depth EstimationVideo Object SegmentationSemantic Segmentation

Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss

2018-12-08 · Lipu Zhou, Jiamin Ye, Montiel Abello, Shengze Wang 외

We present a novel unsupervised learning framework for single view depth estimation using monocular videos. It is well known in 3D vision that enlarging the baseline can increase the depth estimation accuracy, and jointl…

Depth EstimationMonocular Depth EstimationSuper-Resolution

360MonoDepth: High-Resolution 360deg Monocular Depth Estimation

2022-01-01 · CVPR 2022 1 · Manuel Rey-Area, Mingze Yuan, Christian Richardt

360deg cameras can capture complete environments in a single shot, which makes 360deg imagery alluring in many computer vision tasks. However, monocular depth estimation remains a challenge for 360deg data, particula…

2kDepth EstimationGPUMonocular Depth Estimation+2