ICLR 2023 Papers

Recent works have revealed the superiority of feature-level fusion for cross-modal 3D object detection, where fine-grained feature propagation from 2D image pixels to 3D LiDAR points has been widely adopted for performance improvement. Still, the potential of heterogeneous feature propagation between 2D and 3D domains has not been fully explored. In this paper, in contrast to existing pixel-to-point feature propagation, we investigate an opposite point-to-pixel direction, allowing point-wise features to flow inversely into the 2D image branch. Thus, when jointly optimizing the 2D and 3D streams, the gradients back-propagated from the 2D image branch can boost the representation ability of the 3D back-bone network working on LiDAR point clouds. Then, combining pixel-to-point and point-to-pixel information flow mechanisms, we further construct an interactive bidirectional feature propagation framework, dubbed BiProDet. In addition to the architectural design, we also propose normalized local coordinates map estimation, a new 2D auxiliary task for the training of the 2D image branch, which facilitates learning local spatial-aware features from the image modality and implicitly enhances the overall 3D detection performance. Extensive experiments and ablation studies validate the effectiveness of our method. Notably, we rank 1st on the highly competitive KITTI benchmark on the cyclist class by the time of submission. We also uploaded the source code in the supplementary material, which will be publicly available.

Human-centric perception targets for understanding human body pose, shape and segmentation. Pre-training the model on large-scale datasets and fine-tuning it on specific tasks has become a well-established paradigm in human-centric perception. Recently, self-supervised learning methods have re-investigated contrastive learning to achieve superior performance on various downstream tasks. When handling human-centric perception, there still remains untapped potential since 3D human structure information is neglected during the task-agnostic pre-training. In this paper, we propose the Lifting Contrastive Learning (LiftedCL) to obtain 3D-aware human-centric representations which absorb 3D human structure information. In particular, to induce the learning process, a set of 3D skeletons is randomly sampled by resorting to 3D human kinematic prior. With this set of generic 3D samples, 3D human structure information can be learned into 3D-aware representations through adversarial learning. Empirical results demonstrate that LiftedCL outperforms state-of-the-art self-supervised methods on four human-centric downstream tasks, including 2D and 3D human pose estimation (0.4% mAP and 1.8 mm MPJPE improvement on COCO 2D pose estimation and Human3.6M 3D pose estimation), human shape recovery and human parsing.

To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance. Our empirical study, however, suggests that mainstream uncertainty-based and diversity-based active learning policies are not effective when applied in the 3D detection task, as they fail to balance the trade-off between point cloud informativeness and box-level annotation costs. To overcome this limitation, we jointly investigate three novel criteria in our framework CRB for point cloud acquisition - label conciseness, feature representativeness and geometric balance, which hierarchically filters out the point clouds of redundant 3D bounding box labels, latent features and geometric characteristics (e.g., point cloud density) from the unlabeled sample pool and greedily selects informative ones with fewer objects to annotate. Our theoretical analysis demonstrates that the proposed criteria aligns the marginal distributions of the selected subset and the prior distributions of the unseen test set, and minimizes the upper bound of the generalization error. To validate the effectiveness and applicability of CRB, we conduct extensive experiments on the two benchmark 3D object detection datasets of KITTI and Waymo and examine both one-stage (i.e., Second) and two-stage 3D detector (i.e., PV-RCNN). Experiments evidence that the proposed approach outperforms existing active learning strategies and achieves fully supervised performance requiring $1\%$ and $8\%$ annotations of bounding boxes and point clouds, respectively.

3D object detection from multiple image views is a fundamental and challenging task for visual scene understanding. Owing to its low cost and high efficiency, multi-view 3D object detection has demonstrated promising application prospects. However, accurately detecting objects through perspective views is extremely difficult due to the lack of depth information. Current approaches tend to adopt heavy backbones for image encoders, making them inapplicable for real-world deployment. Different from the images, LiDAR points are superior in providing spatial cues, resulting in highly precise localization. In this paper, we explore the incorporation of LiDAR-based detectors for multi-view 3D object detection. Instead of directly training a depth prediction network, we unify the image and LiDAR features in the Bird-Eye-View (BEV) space and adaptively transfer knowledge across non-homogenous representations in a teacher-student paradigm. To this end, we propose BEVDistill, a cross-modal BEV knowledge distillation (KD) framework for multi-view 3D object detection. Extensive experiments demonstrate that the proposed method outperforms current KD approaches on a highly-competitive baseline, BEVFormer, without introducing any extra cost in the inference phase. Notably, our best model achieves 59.4 NDS on the nuScenes test leaderboard, achieving new state-of-the-arts in comparison with various image-based detectors. Code will be available at https://github.com/zehuichen123/BEVDistill.