Multi-modality fusion is proven an effective method for 3d perception for autonomous driving. However, most current multi-modality fusion pipelines for LiDAR semantic segmentation have complicated fusion mechanisms. Point painting is a quite straight forward method which directly bind LiDAR points with visual information. Unfortunately, previous point painting like methods suffer from projection error between camera and LiDAR. In our experiments, we find that this projection error is the devil in point painting. As a result of that, we propose a depth aware point painting mechanism, which significantly boosts the multi-modality fusion. Apart from that, we take a deeper look at the desired visual feature for LiDAR to operate semantic segmentation. By Lifting Visual Information as Cue, LVIC ranks 1st on nuScenes LiDAR semantic segmentation benchmark. Our experiments show the robustness and effectiveness. Codes would be make publicly available soon.
Point encoder is of vital importance for point cloud recognition. As the very beginning step of whole model pipeline, adding features from diverse sources and providing stronger feature encoding mechanism would provide better input for downstream modules. In our work, we proposed a novel PeP module to tackle above issue. PeP contains two main parts, a refined point painting method and a LM-based point encoder. Experiments results on the nuScenes and KITTI datasets validate the superior performance of our PeP. The advantages leads to strong performance on both semantic segmentation and object detection, in both lidar and multi-modal settings. Notably, our PeP module is model agnostic and plug-and-play. Our code will be publicly available soon.
Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often utilize high resolution context modeling, resulting in a computational bottleneck. In this work, we challenge conventional wisdom and introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost. Our approach involves computing self-attention in a fixed low-resolution space regardless of the input image's resolution, with additional 3x3 depth-wise convolutions to capture fine details in the high-resolution space. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure. Extensive experiments on the ADE20K, COCO-Stuff, and Cityscapes datasets demonstrate that LRFormer outperforms state-of-the-art models. The code will be made available at https://github.com/yuhuan-wu/LRFormer.
Datasets that pair Knowledge Graphs (KG) and text together (KG-T) can be used to train forward and reverse neural models that generate text from KG and vice versa. However models trained on datasets where KG and text pairs are not equivalent can suffer from more hallucination and poorer recall. In this paper, we verify this empirically by generating datasets with different levels of noise and find that noisier datasets do indeed lead to more hallucination. We argue that the ability of forward and reverse models trained on a dataset to cyclically regenerate source KG or text is a proxy for the equivalence between the KG and the text in the dataset. Using cyclic evaluation we find that manually created WebNLG is much better than automatically created TeKGen and T-REx. Guided by these observations, we construct a new, improved dataset called LAGRANGE using heuristics meant to improve equivalence between KG and text and show the impact of each of the heuristics on cyclic evaluation. We also construct two synthetic datasets using large language models (LLMs), and observe that these are conducive to models that perform significantly well on cyclic generation of text, but less so on cyclic generation of KGs, probably because of a lack of a consistent underlying ontology.
Human robot interaction is an exciting task, which aimed to guide robots following instructions from human. Since huge gap lies between human natural language and machine codes, end to end human robot interaction models is fair challenging. Further, visual information receiving from sensors of robot is also a hard language for robot to perceive. In this work, HuBo-VLM is proposed to tackle perception tasks associated with human robot interaction including object detection and visual grounding by a unified transformer based vision language model. Extensive experiments on the Talk2Car benchmark demonstrate the effectiveness of our approach. Code would be publicly available in https://github.com/dzcgaara/HuBo-VLM.
Point cloud panoptic segmentation is a challenging task that seeks a holistic solution for both semantic and instance segmentation to predict groupings of coherent points. Previous approaches treat semantic and instance segmentation as surrogate tasks, and they either use clustering methods or bounding boxes to gather instance groupings with costly computation and hand-crafted designs in the instance segmentation task. In this paper, we propose a simple but effective point cloud unified panoptic segmentation (PUPS) framework, which use a set of point-level classifiers to directly predict semantic and instance groupings in an end-to-end manner. To realize PUPS, we introduce bipartite matching to our training pipeline so that our classifiers are able to exclusively predict groupings of instances, getting rid of hand-crafted designs, e.g. anchors and Non-Maximum Suppression (NMS). In order to achieve better grouping results, we utilize a transformer decoder to iteratively refine the point classifiers and develop a context-aware CutMix augmentation to overcome the class imbalance problem. As a result, PUPS achieves 1st place on the leader board of SemanticKITTI panoptic segmentation task and state-of-the-art results on nuScenes.
It is natural to construct a multi-frame instead of a single-frame 3D detector for a continuous-time stream. Although increasing the number of frames might improve performance, previous multi-frame studies only used very limited frames to build their systems due to the dramatically increased computational and memory cost. To address these issues, we propose a novel on-stream training and prediction framework that, in theory, can employ an infinite number of frames while keeping the same amount of computation as a single-frame detector. This infinite framework (INT), which can be used with most existing detectors, is utilized, for example, on the popular CenterPoint, with significant latency reductions and performance improvements. We've also conducted extensive experiments on two large-scale datasets, nuScenes and Waymo Open Dataset, to demonstrate the scheme's effectiveness and efficiency. By employing INT on CenterPoint, we can get around 7% (Waymo) and 15% (nuScenes) performance boost with only 2~4ms latency overhead, and currently SOTA on the Waymo 3D Detection leaderboard.
Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners. To this end, we introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules to capture the spatial and temporal relations accordingly. More Specifically, intra-frame relation module (IntraRM) encapsulates the intra-frame objects into a sparse graph and thus allows us to refine the object features through efficient message passing. On the other hand, inter-frame relation module (InterRM) densely connects each object in its corresponding tracked sequences dynamically, and leverages such temporal information to further enhance its representations efficiently through a lightweight transformer network. We instantiate our novel designs of IntraRM and InterRM with general center-based or anchor-based detectors and evaluate them on Waymo Open Dataset (WOD). With negligible extra overhead, Ret3D achieves the state-of-the-art performance, being 5.5% and 3.2% higher than the recent competitor in terms of the LEVEL 1 and LEVEL 2 mAPH metrics on vehicle detection, respectively.
This paper jointly resolves two problems in vision transformer: i) the computation of Multi-Head Self-Attention (MHSA) has high computational/space complexity; ii) recent vision transformer networks are overly tuned for image classification, ignoring the difference between image classification (simple scenarios, more similar to NLP) and downstream scene understanding tasks (complicated scenarios, rich structural and contextual information). To this end, we note that pyramid pooling has been demonstrated to be effective in various vision tasks owing to its powerful ability in context abstraction, and its natural property of spatial invariance is also suitable to address the loss of structural information (problem ii)). Hence, we propose to adapt pyramid pooling to MHSA for alleviating its high requirement on computational resources (problem i)). In this way, this pooling-based MHSA can well address the above two problems and is thus flexible and powerful for downstream scene understanding tasks. Plugged with our pooling-based MHSA, we build a downstream-task-oriented transformer network, dubbed Pyramid Pooling Transformer (P2T). Extensive experiments demonstrate that, when applied P2T as the backbone network, it shows substantial superiority in various downstream scene understanding tasks such as semantic segmentation, object detection, instance segmentation, and visual saliency detection, compared to previous CNN- and transformer-based networks. The code will be released at https://github.com/yuhuan-wu/P2T.