paper-with-me

홈 › Papers

OASIS-DC: Generalizable Depth Completion via Output-level Alignment of Sparse-Integrated Monocular Pseudo Depth

2026-02-01 · Jaehyeon Cho, Jhonghyun An arxiv

Recent monocular foundation models excel at zero-shot depth estimation, yet their outputs are inherently relative rather than metric, limiting direct use in robotics and autonomous driving. We leverage the fact that relative depth preserves global layout and boundaries: by calibrating it with sparse range measurements, we transform it into a pseudo metric depth prior. Building on this prior, we design a refinement network that follows the prior where reliable and deviates where necessary, enabling accurate metric predictions from very few labeled samples. The resulting system is particularly effective when curated validation data are unavailable, sustaining stable scale and sharp edges across few-shot regimes. These findings suggest that coupling foundation priors with sparse anchors is a practical route to robust, deployment-ready depth completion under real-world label scarcity.

📄 PDF Abstract BibTeX arXiv:2602.01268

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDepth EstimationDepth Completion

Similar Papers 제목 키워드 기반

MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Pose

2022-10-13 · Yang Fu, Ishan Misra, Xiaolong Wang

We propose a generalizable neural radiance fields - MonoNeRF, that can be trained on large-scale monocular videos of moving in static scenes without any ground-truth annotations of depth and camera poses. MonoNeRF follow…

Camera Pose EstimationDecoderDepth EstimationDisentanglement+3

Scale Propagation Network for Generalizable Depth Completion

2024-10-24 · Haotian Wang, Meng Yang, Xinhu Zheng, Gang Hua

Depth completion, inferring dense depth maps from sparse measurements, is crucial for robust 3D perception. Although deep learning based methods have made tremendous progress in this problem, these models cannot generali…

Depth Completion

Attention Sinks and Outliers in Attention Residuals

2026-05-18 · Haozheng Luo, Haoran Dai, Shaoyang Zhang, Xi Chen 외 arxiv

We propose OASIS, an outlier- and sink-aware technique built on inter-layer null signaling. As AttnResidual architectures introduce an additional depth-wise normalization channel, they improve inter-layer routing flexibi…

PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency

2025-07-10 · Haotian Wang, Aoran Xiao, Xiaoqin Zhang, Meng Yang 외

Generalizable depth completion enables the acquisition of dense metric depth maps for unseen environments, offering robust perception capabilities for various downstream tasks. However, training such models typically req…

Depth Completion

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild

2020-07-26 · CVPR 2020 6 · Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima 외

Single-view 3D is the task of recovering 3D properties such as depth and surface normals from a single image. We hypothesize that a major obstacle to single-image 3D is data. We address this issue by presenting Open Anno…

3D geometry