Systematic Evaluation of Depth Backbones and Semantic Cues for Monocular Pseudo-LiDAR 3D Detection

• URL: http://arxiv.org/abs/2601.03617v1
• Date: Wed, 07 Jan 2026 05:57:19 GMT
• Title: Systematic Evaluation of Depth Backbones and Semantic Cues for Monocular Pseudo-LiDAR 3D Detection
• Authors: Samson Oseiwe Ajadalu,
• Abstract summary: We evaluate how depth backbones and feature engineering affect a monocular Pseudo-LiDAR pipeline on the KITTI validation split.<n>Under an off-the-shelf LiDAR detector, depth-backbone choice and geometric fidelity dominate performance, outweighing secondary feature injection.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Monocular 3D object detection offers a low-cost alternative to LiDAR, yet remains less accurate due to the difficulty of estimating metric depth from a single image. We systematically evaluate how depth backbones and feature engineering affect a monocular Pseudo-LiDAR pipeline on the KITTI validation split. Specifically, we compare NeWCRFs (supervised metric depth) against Depth Anything V2 Metric-Outdoor (Base) under an identical pseudo-LiDAR generation and PointRCNN detection protocol. NeWCRFs yields stronger downstream 3D detection, achieving 10.50\% AP$_{3D}$ at IoU$=0.7$ on the Moderate split using grayscale intensity (Exp~2). We further test point-cloud augmentations using appearance cues (grayscale intensity) and semantic cues (instance segmentation confidence). Contrary to the expectation that semantics would substantially close the gap, these features provide only marginal gains, and mask-based sampling can degrade performance by removing contextual geometry. Finally, we report a depth-accuracy-versus-distance diagnostic using ground-truth 2D boxes (including Ped/Cyc), highlighting that coarse depth correctness does not fully predict strict 3D IoU. Overall, under an off-the-shelf LiDAR detector, depth-backbone choice and geometric fidelity dominate performance, outweighing secondary feature injection.

Related papers

• LeAD-M3D: Leveraging Asymmetric Distillation for Real-time Monocular 3D Detection [72.97402509843484]
  LeAD-M3D is a state-of-the-art monocular 3D detector that achieves state-of-the-art accuracy and real-time inference without extra modalities.<n>Asymmetric Augmentation Denoising Distillation (A2D2) transfers geometric knowledge from a clean-image teacher to a mixup-noised student.<n>3D-aware Consistent Matching (CM3D) improves prediction-to-ground truth assignment.<n> Confidence-Gated 3D Inference (CGI3D) accelerates detection by restricting expensive 3D regression to top-confidence regions.
  arXiv  Detail & Related papers  (2025-12-05T12:08:18Z)
• Revisiting Monocular 3D Object Detection with Depth Thickness Field [44.4805861813093]
  We present MonoDTF, a scene-to-instance depth-adapted network for monocular 3D object detection.<n>The framework mainly comprises a Scene-Level Depth Retargeting (SDR) module and an Instance-Level Spatial Refinement (ISR) module.<n>The latter refines the voxel space with the guidance of instances, enhancing the 3D instance-aware capability of the depth thickness field.
  arXiv  Detail & Related papers  (2024-12-26T10:51:50Z)
• DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection [42.07920565812081]
  We propose a novel post-training weight pruning scheme for 3D object detection. It determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence. This framework aims to minimize detection distortion of network output to maximally maintain detection precision.
  arXiv  Detail & Related papers  (2024-07-02T09:33:32Z)
• NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection [72.0098999512727]
  NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by utilizing NeRF to enhance representation learning. We present three corresponding solutions, including semantic enhancement, perspective-aware sampling, and ordinal depth supervision. The resulting algorithm, NeRF-Det++, has exhibited appealing performance in the ScanNetV2 and AR KITScenes datasets.
  arXiv  Detail & Related papers  (2024-02-22T11:48:06Z)
• OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection [51.153003057515754]
  OPA-3D is a single-stage, end-to-end, Occlusion-Aware Pixel-Wise Aggregation network. It jointly estimates dense scene depth with depth-bounding box residuals and object bounding boxes. It outperforms state-of-the-art methods on the main Car category.
  arXiv  Detail & Related papers  (2022-11-02T14:19:13Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud [79.39041453836793]
  We develop a novel single-stage 3D detector for point clouds in an anchor-free manner. We overcome this by converting the voxel-based sparse 3D feature volumes into the sparse 2D feature maps. We propose an IoU-based detection confidence re-calibration scheme to improve the correlation between the detection confidence score and the accuracy of the bounding box regression.
  arXiv  Detail & Related papers  (2021-08-08T13:42:13Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation [81.02742110604161]
  State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern. Our method achieves the 1st place in the leaderboard of Semantic KITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%.
  arXiv  Detail & Related papers  (2020-11-19T18:53:11Z)
• Monocular Depth Prediction through Continuous 3D Loss [16.617016980396865]
  This paper reports a new continuous 3D loss function for learning depth from monocular images. The dense depth prediction from a monocular image is supervised using sparse LIDAR points. Experimental evaluation shows that the proposed loss improves the depth prediction accuracy and produces point-clouds with more consistent 3D geometric structures.
  arXiv  Detail & Related papers  (2020-03-21T22:47:12Z)

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.