SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net

• URL: http://arxiv.org/abs/2403.08885v1
• Date: Wed, 13 Mar 2024 18:12:53 GMT
• Title: SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net
• Authors: Helin Cao, Sven Behnke,
• Abstract summary: SLCF-Net is a novel approach for the Semantic Scene Completion task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. It excels in all SSC metrics and shows great temporal consistency.
• Score: 18.342569823885864
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything. To associate the 2D image features with the 3D scene volume, we introduce Gaussian-decay Depth-prior Projection (GDP). This module projects the 2D features into the 3D volume along the line of sight with a Gaussian-decay function, centered around the depth prior. Volumetric semantics is computed by a 3D U-Net. We propagate the hidden 3D U-Net state using the sensor motion and design a novel loss to ensure temporal consistency. We evaluate our approach on the SemanticKITTI dataset and compare it with leading SSC approaches. The SLCF-Net excels in all SSC metrics and shows great temporal consistency.

Related papers

• CVCP-Fusion: On Implicit Depth Estimation for 3D Bounding Box Prediction [2.0375637582248136]
  Cross-View Center Point-Fusion is a state-of-the-art model to perform 3D object detection. Our architecture utilizes aspects from previously established algorithms, Cross-View Transformers and CenterPoint.
  arXiv  Detail & Related papers  (2024-10-15T02:55:07Z)
• 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)
• NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space [77.6067460464962]
  Monocular 3D Semantic Scene Completion (SSC) has garnered significant attention in recent years due to its potential to predict complex semantics and geometry shapes from a single image, requiring no 3D inputs. We identify several critical issues in current state-of-the-art methods, including the Feature Ambiguity of projected 2D features in the ray to the 3D space, the Pose Ambiguity of the 3D convolution, and the Imbalance in the 3D convolution across different depth levels. We devise a novel Normalized Device Coordinates scene completion network (NDC-Scene) that directly extends the 2
  arXiv  Detail & Related papers  (2023-09-26T02:09:52Z)
• DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction [51.96971077984869]
  Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. This work proposes Density Volume Construction Network (DevNet), a novel self-supervised monocular depth learning framework.
  arXiv  Detail & Related papers  (2022-09-14T00:08:44Z)
• Semantic Dense Reconstruction with Consistent Scene Segments [33.0310121044956]
  A method for dense semantic 3D scene reconstruction from an RGB-D sequence is proposed to solve high-level scene understanding tasks. First, each RGB-D pair is consistently segmented into 2D semantic maps based on a camera tracking backbone. A dense 3D mesh model of an unknown environment is incrementally generated from the input RGB-D sequence.
  arXiv  Detail & Related papers  (2021-09-30T03:01:17Z)
• 3D-to-2D Distillation for Indoor Scene Parsing [78.36781565047656]
  We present a new approach that enables us to leverage 3D features extracted from large-scale 3D data repository to enhance 2D features extracted from RGB images. First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2D features during the training. Second, we design a two-stage dimension normalization scheme to calibrate the 2D and 3D features for better integration. Third, we design a semantic-aware adversarial training model to extend our framework for training with unpaired 3D data.
  arXiv  Detail & Related papers  (2021-04-06T02:22:24Z)
• Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation [81.08111209632501]
  We propose a geometry-aware stereo-LiDAR fusion network for long-range depth estimation. We exploit sparse and accurate point clouds as a cue for guiding correspondences of stereo images in a unified 3D volume space. Our network achieves state-of-the-art performance on the KITTI and the Virtual- KITTI datasets.
  arXiv  Detail & Related papers  (2021-03-24T03:24:46Z)
• S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds [0.16799377888527683]
  We present S3CNet, a sparse convolution based neural network that predicts the semantically completed scene from a single, unified LiDAR point cloud. We show that our proposed method outperforms all counterparts on the 3D task, achieving state-of-the art results on the Semantic KITTI benchmark.
  arXiv  Detail & Related papers  (2020-12-16T20:14:41Z)
• Depth Based Semantic Scene Completion with Position Importance Aware Loss [52.06051681324545]
  PALNet is a novel hybrid network for semantic scene completion. It extracts both 2D and 3D features from multi-stages using fine-grained depth information. It is beneficial for recovering key details like the boundaries of objects and the corners of the scene.
  arXiv  Detail & Related papers  (2020-01-29T07:05:52Z)

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.