Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Function

• URL: http://arxiv.org/abs/2403.16888v2
• Date: Sat, 23 Nov 2024 12:00:05 GMT
• Title: Towards Balanced RGB-TSDF Fusion for Consistent Semantic Scene Completion by 3D RGB Feature Completion and a Classwise Entropy Loss Function
• Authors: Laiyan Ding, Panwen Hu, Jie Li, Rui Huang,
• Abstract summary: RGB-TSDF fusion has been considered nontrivial and commonly-used naive addition will result in inconsistent results. We propose a two-stage network with a 3D RGB feature completion module that completes RGB features with meaningful values for occluded areas.
• Score: 10.22925811541619
• License:
• Abstract: Semantic Scene Completion (SSC) aims to jointly infer semantics and occupancies of 3D scenes. Truncated Signed Distance Function (TSDF), a 3D encoding of depth, has been a common input for SSC. Furthermore, RGB-TSDF fusion, seems promising since these two modalities provide color and geometry information, respectively. Nevertheless, RGB-TSDF fusion has been considered nontrivial and commonly-used naive addition will result in inconsistent results. We argue that the inconsistency comes from the sparsity of RGB features upon projecting into 3D space, while TSDF features are dense, leading to imbalanced feature maps when summed up. To address this RGB-TSDF distribution difference, we propose a two-stage network with a 3D RGB feature completion module that completes RGB features with meaningful values for occluded areas. Moreover, we propose an effective classwise entropy loss function to punish inconsistency. Extensive experiments on public datasets verify that our method achieves state-of-the-art performance among methods that do not adopt extra data.

Related papers

• Semantic Scene Completion with Multi-Feature Data Balancing Network [5.3431413737671525]
  We propose a dual-head model for RGB and depth data (F-TSDF) inputs. Our hybrid encoder-decoder architecture with identity transformation in a pre-activation residual module effectively manages diverse signals within F-TSDF. We evaluate RGB feature fusion strategies and use a combined loss function cross entropy for 2D RGB features and weighted cross-entropy for 3D SSC predictions.
  arXiv  Detail & Related papers  (2024-12-02T12:12:21Z)
• Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set [49.780302894956776]
  It is vital to infer a signed distance function (SDF) in multi-view based surface reconstruction. We propose a method that seamlessly merge 3DGS with the learning of neural SDFs. Our numerical and visual comparisons show our superiority over the state-of-the-art results on the widely used benchmarks.
  arXiv  Detail & Related papers  (2024-10-18T05:48:06Z)
• Channel and Spatial Relation-Propagation Network for RGB-Thermal Semantic Segmentation [10.344060599932185]
  RGB-Thermal (RGB-T) semantic segmentation has shown great potential in handling low-light conditions. The key to RGB-T semantic segmentation is to effectively leverage the complementarity nature of RGB and thermal images.
  arXiv  Detail & Related papers  (2023-08-24T03:43:47Z)
• Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution [123.04455334124188]
  Guided depth map super-resolution (GDSR) aims to upsample low-resolution (LR) depth maps with additional information involved in high-resolution (HR) RGB images from the same scene. In this paper, we propose the Spherical Space feature Decomposition Network (SSDNet) to solve the above issues. Our method can achieve state-of-the-art results on four test datasets, as well as successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2023-03-15T21:22:21Z)
• Robust RGB-D Fusion for Saliency Detection [13.705088021517568]
  We propose a robust RGB-D fusion method that benefits from layer-wise and trident spatial, attention mechanisms. Our experiments on five benchmark datasets demonstrate that the proposed fusion method performs consistently better than the state-of-the-art fusion alternatives.
  arXiv  Detail & Related papers  (2022-08-02T21:23:00Z)
• Pyramidal Attention for Saliency Detection [30.554118525502115]
  This paper exploits only RGB images, estimates depth from RGB, and leverages the intermediate depth features. We employ a pyramidal attention structure to extract multi-level convolutional-transformer features to process initial stage representations. We report significantly improved performance against 21 and 40 state-of-the-art SOD methods on eight RGB and RGB-D datasets.
  arXiv  Detail & Related papers  (2022-04-14T06:57:46Z)
• RGB-D Salient Object Detection via 3D Convolutional Neural Networks [19.20231385522917]
  We make the first attempt in addressing RGB-D SOD through 3D convolutional neural networks. The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage. We show that RD3D performs favorably against 14 state-of-the-art RGB-D SOD approaches in terms of four key evaluation metrics.
  arXiv  Detail & Related papers  (2021-01-25T17:03:02Z)
• MobileSal: Extremely Efficient RGB-D Salient Object Detection [62.04876251927581]
  This paper introduces a novel network, methodname, which focuses on efficient RGB-D salient object detection (SOD) We propose an implicit depth restoration (IDR) technique to strengthen the feature representation capability of mobile networks for RGB-D SOD. With IDR and CPR incorporated, methodnameperforms favorably against sArt methods on seven challenging RGB-D SOD datasets.
  arXiv  Detail & Related papers  (2020-12-24T04:36:42Z)
• Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection [73.31632581915201]
  We propose a novel data-level recombination strategy to fuse RGB with D (depth) before deep feature extraction. A newly lightweight designed triple-stream network is applied over these novel formulated data to achieve an optimal channel-wise complementary fusion status between the RGB and D.
  arXiv  Detail & Related papers  (2020-08-07T10:13:05Z)
• Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation [59.94819184452694]
  Depth information has proven to be a useful cue in the semantic segmentation of RGBD images for providing a geometric counterpart to the RGB representation. Most existing works simply assume that depth measurements are accurate and well-aligned with the RGB pixels and models the problem as a cross-modal feature fusion. In this paper, we propose a unified and efficient Crossmodality Guided to not only effectively recalibrate RGB feature responses, but also to distill accurate depth information via multiple stages and aggregate the two recalibrated representations alternatively.
  arXiv  Detail & Related papers  (2020-07-17T18:35:24Z)
• Cross-Modal Weighting Network for RGB-D Salient Object Detection [76.0965123893641]
  We propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD. Specifically, three RGB-depth interaction modules, named CMW-L, CMW-M and CMW-H, are developed to deal with respectively low-, middle- and high-level cross-modal information fusion. CMWNet consistently outperforms 15 state-of-the-art RGB-D SOD methods on seven popular benchmarks.
  arXiv  Detail & Related papers  (2020-07-09T16:01:44Z)

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.