In this paper, we propose a fast decision scheme using a lightweight neural network (LNN) to avoid redundant block partitioning in versatile video coding (VVC). A more versatile block structure, named the multi-type tree (MTT) structure, which includes binary trees (BTs) and ternary trees (TTs), is adopted by VCC, in addition to the traditional quadtree structure. The MTT improved the coding efficiency compared with previous video coding standards. However, the new tree structures, mainly TT, significantly increased the complexity of the VVC encoder. Although widespread application of VVC has been inhibited, this problem has not yet been investigated thoroughly in the literature. In this study, we first determine the statistical characteristics of coded parameters that exhibit correlation with the TT and develop two useful types of features—explicit VVC features (EVFs) and derived VVC features (DVFs)—to facilitate the intra coding of VVC. These features can be obtained efficiently during the intra prediction before the determination of the best block partitioning during rate-distortion optimization in VVC encoding. Our LNN model decides whether to terminate the nested TT block structures subsequent to a quadtree based on the features. The experimental results confirm that the proposed method substantially decreases the encoding complexity of VVC with a slight coding loss under the All Intra configuration. Our code, models, and dataset are available at https://github.com/foriamweak/MTTPartitioning_LNN.

This paper presents a fast encoding method for versatile video coding (VVC) using an early determination scheme that skips redundant multi-type tree (MTT) pruning. MTT consists of binary and ternary trees (TTs) with traditional quadtrees and has recently attracted considerable VVC research interest due to coding efficiency beyond HEVC. However, the additional trees, particularly TTs, significantly increased VVC complexity, which has rarely been studied previously. Therefore, we identified TT characteristics in the VVC encoding context, and hence propose a simple early decision technique that can effectively reduce TT complexity. Experiments over various test sequences show that the proposed method substantially decreased the total encoding time for a VVC test model 4.0 (VTM 4.0) with only slight coding loss under the all-intra configuration. In particular, the proposed method reduced TT encoding time by up to 66% compared with VTM 4.0.

In this paper, we propose a fast encoding method to facilitate an affine motion estimation (AME) process in versatile video coding (VVC) encoders. The recently-launched VVC project for next-generation video coding standardization far outperforms the High Efficiency Video Coding (HEVC) standard in terms of coding efficiency. The first version of the VVC test model (VTM) displays superior coding efficiency yet requires higher encoding complexity due to advanced inter-prediction techniques of the multi-type tree (MTT) structure. In particular, an AME technique in VVC is designed to reduce temporal redundancies (other than translational motion) in dynamic motions, thus achieving more accurate motion prediction. The VTM encoder, however, requires considerable computational complexity because of the AME process in the recursive MTT partitioning. In this paper, we introduce useful features that reflect the statistical characteristics of MTT and AME and propose a method that employs these features to skip redundant AME processes. Experimental results show that—when compared to VTM 3.0—the proposed method reduces the AME time of VTM to 63% on average, while the coding loss is within 0.1% in the random-access configuration.

LiDAR-based 3D object detection has been widely utilized in fields such as autonomous driving and robotics. However, the black-box nature of 3D models limits their interpretability, making it difficult to understand their predictions and evaluate significant feature contributions, which are essential for safety-critical applications. To address this, we propose a novel knowledge distillation method for 3D object detection that integrates explanation-based and aggregation techniques to achieve effective knowledge transfer and, as a result, enhance the model’s interpretability. Our method generates attribution maps that highlight the importance of 3D points in the teacher model and aggregates them into a single map. This map is aligned with the student model’s pillar features using corresponding coordinates, allowing pillar-wise feature mapping. Building on this feature mapping, to the best of our knowledge, this is the first study to propose a distillation process that effectively transfers the teacher model’s explanations of critical regions to the student model. Experimental results demonstrate that the proposed method increases 3D and BEV mAP by up to 2.09% and 0.84%, respectively, compared to the existing models.

In the video compression industry, video compression tailored to machine vision tasks has recently emerged as a critical area of focus. Given the unique characteristics of machine vision, the current practice of directly employing conventional codecs reveals inefficiency, which requires compressing unnecessary regions. In this paper, we propose a framework that more aptly encodes video regions distinguished by machine vision to enhance coding efficiency. For that, the proposed framework consists of deep learning-based adaptive switch networks that guide the efficient coding tool for video encoding. Through the experiments, it is demonstrated that the proposed framework has superiority over the latest standardization project, video coding for machine benchmark, which achieves a Bjontegaard delta (BD)-rate gain of 5.91% on average and reaches up to a 19.51% BD-rate gain.

The authors propose a compression strategy for a 3D human pose estimation model based on a transformer which yields high accuracy but increases the model size. This approach involves a pruning‐guided determination of the search range to achieve lightweight pose estimation under limited training time and to identify the optimal model size. In addition, the authors propose a transformer‐based feature distillation (TFD) method, which efficiently exploits the pose estimation model in terms of both model size and accuracy by leveraging transformer architecture characteristics. Pruning‐guided TFD is the first approach for 3D human pose estimation that employs transformer architecture. The proposed approach was tested on various extensive data sets, and the results show that it can reduce the model size by 30% compared to the state‐of‐the‐art while ensuring high accuracy.