Zhang, Z;
Ling, P;
Xu, Z;
Yang, W;
Liao, Q;
Xue, JH;
(2025)
BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network.
IEEE Transactions on Circuits and Systems for Video Technology
10.1109/TCSVT.2025.3636155.
(In press).
Preview |
PDF
BDC-Occ_Binarized_Deep_Convolution_Unit_For_Binarized_Occupancy_Network.pdf - Accepted Version Download (13MB) | Preview |
Abstract
Existing 3D occupancy networks demand significant hardware resources, hindering the deployment of resource-limited devices. Binarized Neural Networks (BNNs) offer a potential solution by substantially reducing computational and memory requirements. However, their performance decrease notably compared to full-precision networks. In addition, it is challenging to enhance the performance of the binarized model by increasing the number of binarized convolutional layers, which limits its practicability for 3D occupancy prediction. In this paper, we reconsider the components in binarized convolutional layers, and structures, for 3D occupancy prediction task. Two original insights into binarized convolution are presented, substantiated with theoretical proofs: (a) 1×1 binarized convolution introduces minimal binarization errors as the network deepens, and (b) binarized convolution is inferior to full-precision convolution in capturing cross-channel feature importance. Building on the above insights, we propose a novel binarized deep convolution (BDC) unit that significantly enhances performance, even when the number of binarized convolutional layers increases to meet the requirements of 3D occupancy networks. Specifically, in the BDC unit, additional binarized convolutional kernels are constrained to 1×1 to minimize the effects of binarization errors. Further, we propose a per-channel refinement branch to reweight the output via first-order approximation. Then, we partition the 3D occupancy networks into four distinct convolutional modules, employing BDC units to explore the effects of binarizing each of these modules. The proposed BDC unit minimizes binarization errors and improves perceptual capability, meeting the stringent requirements for accuracy and computational efficiency in 3D occupancy prediction. Extensive quantitative and qualitative experiments demonstrate that the proposed BDC unit achieves state-of-the-art performance in 3D occupancy prediction and 3D object detection tasks, while significantly reducing parameters and computational costs. This highlights the potential of the BDC unit as an efficient fundamental component in binarized 3D occupancy networks.
| Type: | Article |
|---|---|
| Title: | BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/TCSVT.2025.3636155 |
| Publisher version: | https://doi.org/10.1109/tcsvt.2025.3636155 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Three-dimensional displays , Convolution , Computational modeling , Convolutional neural networks , Solid modeling , Performance evaluation , Convolutional codes , Computational efficiency , Accuracy , Videos |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10218826 |
Archive Staff Only
 |
View Item |
