paper-with-me

Papers Surface Normal Estimation

“Surface Normal Estimation” 태그가 달린 논문 96편 · 필터 해제

Probabilistic Online Event Downsampling

2025-06-03 · Andreu Girbau-Xalabarder, Jun Nagata, Shinichi Sumiyoshi

Event cameras capture scene changes asynchronously on a per-pixel basis, enabling extremely high temporal resolution. However, this advantage comes at the cost of high bandwidth, memory, and computational demands. To add…

object-detectionObject DetectionSurface Normal Estimation

Robust and Real-time Surface Normal Estimation from Stereo Disparities using Affine Transformations

2025-04-21 · Csongor Csanad Kariko, Muhammad Rafi Faisal, Levente Hajder

This work introduces a novel method for surface normal estimation from rectified stereo image pairs, leveraging affine transformations derived from disparity values to achieve fast and accurate results. We demonstrate ho…

GPUSurface Normal Estimation

NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors

2025-04-15 · Yanrui Bin, WenBo Hu, Haoyuan Wang, Xinya Chen 외

Surface normal estimation serves as a cornerstone for a spectrum of computer vision applications. While numerous efforts have been devoted to static image scenarios, ensuring temporal coherence in video-based normal esti…

Surface Normal Estimation

LiSu: A Dataset and Method for LiDAR Surface Normal Estimation

2025-03-11 · CVPR 2025 1 · Dušan Malić, Christian Fruhwirth-Reisinger, Samuel Schulter, Horst Possegger

While surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored. This is caused by the lack of large-scale annotated datasets on the on…

Autonomous DrivingDomain AdaptationSurface Normal EstimationSurface Reconstruction

Image Gradient-Aided Photometric Stereo Network

2024-12-16 · Kaixuan Wang, Lin Qi, Shiyu Qin, Kai Luo 외

Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations. Recent deep learning-based PS methods often overlook the complexity of object surfac…

regressionSurface Normal Estimation

Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images

2024-11-04 · Kun Huang, Fang-Lue Zhang, Fangfang Zhang, Yu-Kun Lai 외

Geometric estimation is required for scene understanding and analysis in panoramic 360{\deg} images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, e…

Multi-Task LearningScene UnderstandingSurface Normal Estimation

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

2024-09-17 · Gonzalo Martin Garcia, Karim Abou Zeid, Christian Schmidt, Daan de Geus 외

Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state…

Conditional Image GenerationDepth EstimationImage GenerationMonocular Depth Estimation+2

Sapiens: Foundation for Human Vision Models

2024-08-22 · Rawal Khirodkar, Timur Bagautdinov, Julieta Martinez, Su Zhaoen 외

We present Sapiens, a family of models for four fundamental human-centric vision tasks -- 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-r…

2D Human Pose Estimation2D Pose EstimationDepth EstimationHuman Part Segmentation+3

Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration

2024-08-18 · Hao Ai, Lin Wang

360 cameras capture the entire surrounding environment with a large FoV, exhibiting comprehensive visual information to directly infer the 3D structures, e.g., depth and surface normal, and semantic information simultane…

3D geometryERPMulti-Task LearningSemantic Segmentation+1

StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

2024-06-24 · Chongjie Ye, Lingteng Qiu, Xiaodong Gu, Qi Zuo 외

This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized by repurposing diffusion priors. However…

Surface Normal EstimationSurface Reconstruction

PanoNormal: Monocular Indoor 360° Surface Normal Estimation

2024-05-29 · Kun Huang, FangLue Zhang, Neil Dodgson

The presence of spherical distortion on the Equirectangular image is an acknowledged challenge in dense regression computer vision tasks, such as surface normal estimation. Recent advances in convolutional neural network…

Surface Normal Estimation

Enabling Visual Recognition at Radio Frequency

2024-05-29 · Haowen Lai, Gaoxiang Luo, Yifei Liu, Mingmin Zhao

This paper introduces PanoRadar, a novel RF imaging system that brings RF resolution close to that of LiDAR, while providing resilience against conditions challenging for optical signals. Our LiDAR-comparable 3D imaging …

object-detectionObject DetectionSemantic SegmentationSurface Normal Estimation

Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation

2024-03-22 · Under review for Transaction 2024 4 · Mu Hu, Wei Yin, Chi Zhang, Zhipeng Cai 외

We introduce Metric3D v2, a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image, which is crucial for metric 3D recovery. While depth and normal are geometrically relat…

Depth EstimationSurface Normal EstimationZero-shot Generalization

Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning

2024-03-15 · Meixuan Li, Tianyu Li, Guoqing Wang, Peng Wang 외

In this study, we address the intricate challenge of multi-task dense prediction, encompassing tasks such as semantic segmentation, depth estimation, and surface normal estimation, particularly when dealing with partiall…

Depth EstimationSemantic SegmentationSurface Normal Estimation

What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?

2024-03-10 · Guangkai Xu, Yongtao Ge, MingYu Liu, Chengxiang Fan 외

Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent works show promising results by simply f…

Depth EstimationImage MattingImage SegmentationMonocular Depth Estimation+3

Rethinking Inductive Biases for Surface Normal Estimation

2024-03-01 · CVPR 2024 1 · Gwangbin Bae, Andrew J. Davison

Despite the growing demand for accurate surface normal estimation models, existing methods use general-purpose dense prediction models, adopting the same inductive biases as other tasks. In this paper, we discuss the ind…

Surface Normal Estimation

Surface Normal Estimation with Transformers

2024-01-11 · Barry Shichen Hu, Siyun Liang, Johannes Paetzold, Huy H. Nguyen 외

We propose the use of a Transformer to accurately predict normals from point clouds with noise and density variations. Previous learning-based methods utilize PointNet variants to explicitly extract multi-scale features …

Surface Normal Estimation

Event-based Shape from Polarization with Spiking Neural Networks

2023-12-26 · Peng Kang, Srutarshi Banerjee, Henry Chopp, Aggelos Katsaggelos 외

Recent advances in event-based shape determination from polarization offer a transformative approach that tackles the trade-off between speed and accuracy in capturing surface geometries. In this paper, we investigate ev…

Surface Normal Estimation

RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation

2023-11-21 · Tutian Tang, Jiyu Liu, Jieyi Zhang, Haoyuan Fu 외

Transparent objects are widely used in our daily lives, making it important to teach robots to interact with them. However, it's not easy because the reflective and refractive effects can make depth cameras fail to give …

global-optimizationSurface Normal EstimationTransparent objects

PolyMaX: General Dense Prediction with Mask Transformer

2023-11-09 · Xuan Yang, Liangzhe Yuan, Kimberly Wilber, Astuti Sharma 외

Dense prediction tasks, such as semantic segmentation, depth estimation, and surface normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or regression (continuous outputs). This per…

Depth EstimationMonocular Depth EstimationPredictionSemantic Segmentation+2
1–20 / 96 다음 →