Lune

ICCV2023Top-tier venue

SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments

Jongsung Lee, Gyeongsu Cho, Jeongin Park, Kyongjun Kim, Seongoh Lee, Jung-Hee Kim, Seong-Gyun Jeong, Kyungdon Joo

Abstract

Although 3D perception for autonomous vehicles has focused on frontal-view information, more than half of fatal accidents occur due to side impacts in practice (e.g., T-bone crash). Motivated by this fact, we investigate the problem of side-view depth estimation, especially for monocular fisheye cameras, which provide wide FoV information. However, since fisheye cameras head road areas, it observes road areas mostly and results in severe distortion on object areas, such as vehicles or pedestrians. To alleviate these issues, we propose a new fisheye depth estimation network, SlaBins, that infers an accurate and dense depth map based on a geometric property of road environments; most objects are standing (i.e., orthogonal) on the road environments. Concretely, we introduce a slanted multi-cylindrical image (MCI) representation, which allows us to describe a distance as a radius to a cylindrical layer orthogonal to the ground regardless of the camera viewing direction. Based on the slanted MCI, we estimate a set of adaptive bins and a per-pixel probability map for depth estimation. Then by combining it with the estimated slanted angle of viewing direction, we directly infer a dense and accurate depth map for fisheye cameras. Experiments demonstrate that SlaBins outperforms the state-of-the-art methods in both qualitative and quantitative evaluation on the SynWoodScape and KITTI-360 depth datasets. For more information, you can visit our project page https://syniez.github.io/SlaBins/ .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior cites Vision Transformers for Dense Prediction
  • P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior cites Adaptive Surface Normal Constraint for Depth Estimation
  • Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images cites Vision Transformers for Dense Prediction
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric FusionZhiwei Zhang, Ruikai Xu, Weijian Zhang, Zhizhong Zhang et al.ACM MM 2025 · 2 citations
  2. HUSH: Holistic Panoramic 3D Scene Understanding using Spherical HarmonicsJongsung Lee, Harin Park, Byeong-Uk Lee, Kyungdon JooCVPR 2025

Builds on9

  1. Vision Transformers for Dense PredictionRené Ranftl, Alexey Bochkovskiy, Vladlen KoltunICCV 2021 · 2,647 citations
  2. PETRv2: A Unified Framework for 3D Perception from Multi-Camera ImagesYingfei Liu, Junjie Yan, Fan Jia, Shuailin Li et al.ICCV 2023 · 513 citations
  3. P3Depth: Monocular Depth Estimation with a Piecewise Planarity PriorVaishakh Patil, Christos Sakaridis, Alexander Liniger, Luc Van GoolCVPR 2022 · 144 citations
  4. Adaptive Surface Normal Constraint for Depth EstimationXiaoxiao Long, Cheng Lin, Lingjie Liu, Wei Li et al.ICCV 2021 · 75 citations
  5. Single-View View Synthesis in the Wild with Learned Adaptive Multiplane ImagesYuxuan Han, Ruicheng Wang, Jiaolong YangSIGGRAPH 2022 · 65 citations

Related papers

  1. MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth CluesJinrang Jia, Zhenjia Li, Yifeng ShiNeurIPS 2023 · 69 citations
  2. Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry ConstraintsRuijin Liu, Dapeng Chen, Tie Liu, Zhiliang Xiong et al.AAAI 2022 · 64 citations
  3. WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous DrivingSenthil Kumar Yogamani, Christian Witt, Hazem Rashed, Sanjaya Nayak et al.ICCV 2019 · 325 citations
  4. SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth EstimationYi Zhu, Hao Xiong, Lin Xiao, Ranfeng Shi et al.CVPR 2026
  5. Estimating Egocentric 3D Human Pose in Global SpaceJian Wang, Lingjie Liu, Weipeng Xu, Kripasindhu Sarkar et al.ICCV 2021 · 78 citations
Dusk over the sea between two cliffs drawn in fine vertical lines