UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing

Human pose plays a crucial role in the digital age. While recent works have achieved impressive progress in understanding and generating human poses, they often support only a single modality of control signals and operate in isolation, limiting their application in real-world scenarios. This paper presents UniPose, a framework employing Large Language Models (LLMs) to comprehend, generate, and edit human poses across various modalities, including images, text, and 3D SMPL poses. Specifically, we apply a pose tokenizer to convert 3D poses into discrete pose tokens, enabling seamless integration into the LLM within a unified vocabulary. To further enhance the fine-grained pose perception capabilities, we facilitate UniPose with a mixture of visual encoders, among them a pose-specific visual encoder. Benefiting from a unified learning strategy, UniPose effectively transfers knowledge across different pose-relevant tasks, adapts to unseen tasks, and exhibits extended capabilities. This work serves as the first attempt at building a general-purpose framework for pose comprehension, generation, and editing. Extensive experiments highlight UniPose's competitive and even superior performance across various pose-relevant tasks.

Mitigating Object Hallucination via Concentric Causal Attention

Recent Large Vision Language Models (LVLMs) present remarkable zero-shot conversational and reasoning capabilities given multimodal queries. Nevertheless, they suffer from object hallucination, a phenomenon where LVLMs are prone to generate textual responses not factually aligned with image inputs. Our pilot study reveals that object hallucination is closely tied with Rotary Position Encoding (RoPE), a widely adopted positional dependency modeling design in existing LVLMs. Due to the long-term decay in RoPE, LVLMs tend to hallucinate more when relevant visual cues are distant from instruction tokens in the multimodal input sequence. Additionally, we observe a similar effect when reversing the sequential order of visual tokens during multimodal alignment. Our tests indicate that long-term decay in RoPE poses challenges to LVLMs while capturing visual-instruction interactions across long distances. We propose Concentric Causal Attention (CCA), a simple yet effective positional alignment strategy that mitigates the impact of RoPE long-term decay in LVLMs by naturally reducing relative distance between visual and instruction tokens. With CCA, visual tokens can better interact with instruction tokens, thereby enhancing model's perception capability and alleviating object hallucination. Without bells and whistles, our positional alignment method surpasses existing hallucination mitigation strategies by large margins on multiple object hallucination benchmarks.

Learning Content-Aware Multi-Modal Joint Input Pruning via Bird's-Eye-View Representation

In the landscape of autonomous driving, Bird's-Eye-View (BEV) representation has recently garnered substantial academic attention, serving as a transformative framework for the fusion of multi-modal sensor inputs. This BEV paradigm effectively shifts the sensor fusion challenge from a rule-based methodology to a data-centric approach, thereby facilitating more nuanced feature extraction from an array of heterogeneous sensors. Notwithstanding its evident merits, the computational overhead associated with BEV-based techniques often mandates high-capacity hardware infrastructures, thus posing challenges for practical, real-world implementations. To mitigate this limitation, we introduce a novel content-aware multi-modal joint input pruning technique. Our method leverages BEV as a shared anchor to algorithmically identify and eliminate non-essential sensor regions prior to their introduction into the perception model's backbone. We validatethe efficacy of our approach through extensive experiments on the NuScenes dataset, demonstrating substantial computational efficiency without sacrificing perception accuracy. To the best of our knowledge, this work represents the first attempt to alleviate the computational burden from the input pruning point.

QuadBEV: An Efficient Quadruple-Task Perception Framework via Bird's-Eye-View Representation

Bird's-Eye-View (BEV) perception has become a vital component of autonomous driving systems due to its ability to integrate multiple sensor inputs into a unified representation, enhancing performance in various downstream tasks. However, the computational demands of BEV models pose challenges for real-world deployment in vehicles with limited resources. To address these limitations, we propose QuadBEV, an efficient multitask perception framework that leverages the shared spatial and contextual information across four key tasks: 3D object detection, lane detection, map segmentation, and occupancy prediction. QuadBEV not only streamlines the integration of these tasks using a shared backbone and task-specific heads but also addresses common multitask learning challenges such as learning rate sensitivity and conflicting task objectives. Our framework reduces redundant computations, thereby enhancing system efficiency, making it particularly suited for embedded systems. We present comprehensive experiments that validate the effectiveness and robustness of QuadBEV, demonstrating its suitability for real-world applications.

WOMD-Reasoning: A Large-Scale Language Dataset for Interaction and Driving Intentions Reasoning

We propose Waymo Open Motion Dataset-Reasoning (WOMD-Reasoning), a language annotation dataset built on WOMD, with a focus on describing and reasoning interactions and intentions in driving scenarios. Previous language datasets primarily captured interactions caused by close distances. However, interactions induced by traffic rules and human intentions, which can occur over long distances, are yet sufficiently covered, despite being very common and more challenging for prediction or planning models to understand. Therefore, our WOMD-Reasoning focuses extensively on these interactions, providing a total of 409k Q&As for varying types of interactions. Additionally, WOMD-Reasoning presents by far the largest Q&A dataset on real-world driving scenarios, with around 3 million Q&As covering various topics of autonomous driving from map descriptions, motion status descriptions, to narratives and analyses of agents' interactions, behaviors, and intentions. This extensive textual information enables fine-tuning driving-related Large Language Models (LLMs) for a wide range of applications like scene description, prediction, planning, etc. By incorporating interaction and intention language from WOMD-Reasoning, we see significant enhancements in the performance of the state-of-the-art trajectory prediction model, Multipath++, with improvements of 10.14% in $MR_6$ and 6.90% in $minFDE_6$, proving the effectiveness of WOMD-Reasoning. We hope WOMD-Reasoning would empower LLMs in driving to offer better interaction understanding and behavioral reasoning. The dataset is available on https://waymo.com/open/download .

Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment

In this paper, we point out suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the entire noise space, resulting in a mixture of all images at every point in the noise layer. We emphasize that this random mixture of noise-data mapping complicates the optimization of the denoising function in diffusion models. Drawing inspiration from the immiscible phenomenon in physics, we propose Immiscible Diffusion, a simple and effective method to improve the random mixture of noise-data mapping. In physics, miscibility can vary according to various intermolecular forces. Thus, immiscibility means that the mixing of the molecular sources is distinguishable. Inspired by this, we propose an assignment-then-diffusion training strategy. Specifically, prior to diffusing the image data into noise, we assign diffusion target noise for the image data by minimizing the total image-noise pair distance in a mini-batch. The assignment functions analogously to external forces to separate the diffuse-able areas of images, thus mitigating the inherent difficulties in diffusion training. Our approach is remarkably simple, requiring only one line of code to restrict the diffuse-able area for each image while preserving the Gaussian distribution of noise. This ensures that each image is projected only to nearby noise. To address the high complexity of the assignment algorithm, we employ a quantized-assignment method to reduce the computational overhead to a negligible level. Experiments demonstrate that our method achieve up to 3x faster training for consistency models and DDIM on the CIFAR dataset, and up to 1.3x faster on CelebA datasets for consistency models. Besides, we conduct thorough analysis about the Immiscible Diffusion, which sheds lights on how it improves diffusion training speed while improving the fidelity.

SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception

Multi-modal 3D object detection has exhibited significant progress in recent years. However, most existing methods can hardly scale to long-range scenarios due to their reliance on dense 3D features, which substantially escalate computational demands and memory usage. In this paper, we introduce SparseFusion, a novel multi-modal fusion framework fully built upon sparse 3D features to facilitate efficient long-range perception. The core of our method is the Sparse View Transformer module, which selectively lifts regions of interest in 2D image space into the unified 3D space. The proposed module introduces sparsity from both semantic and geometric aspects which only fill grids that foreground objects potentially reside in. Comprehensive experiments have verified the efficiency and effectiveness of our framework in long-range 3D perception. Remarkably, on the long-range Argoverse2 dataset, SparseFusion reduces memory footprint and accelerates the inference by about two times compared to dense detectors. It also achieves state-of-the-art performance with mAP of 41.2% and CDS of 32.1%. The versatility of SparseFusion is also validated in the temporal object detection task and 3D lane detection task. Codes will be released upon acceptance.

Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approach

3D object detection in Bird's-Eye-View (BEV) space has recently emerged as a prevalent approach in the field of autonomous driving. Despite the demonstrated improvements in accuracy and velocity estimation compared to perspective view methods, the deployment of BEV-based techniques in real-world autonomous vehicles remains challenging. This is primarily due to their reliance on vision-transformer (ViT) based architectures, which introduce quadratic complexity with respect to the input resolution. To address this issue, we propose an efficient BEV-based 3D detection framework called BEVENet, which leverages a convolutional-only architectural design to circumvent the limitations of ViT models while maintaining the effectiveness of BEV-based methods. Our experiments show that BEVENet is 3$\times$ faster than contemporary state-of-the-art (SOTA) approaches on the NuScenes challenge, achieving a mean average precision (mAP) of 0.456 and a nuScenes detection score (NDS) of 0.555 on the NuScenes validation dataset, with an inference speed of 47.6 frames per second. To the best of our knowledge, this study stands as the first to achieve such significant efficiency improvements for BEV-based methods, highlighting their enhanced feasibility for real-world autonomous driving applications.

Pre-training on Synthetic Driving Data for Trajectory Prediction

Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim to tackle the challenge of learning general trajectory forecasting representations under limited data availability. We propose to augment both HD maps and trajectories and apply pre-training strategies on top of them. Specifically, we take advantage of graph representations of HD-map and apply vector transformations to reshape the maps, to easily enrich the limited number of scenes. Additionally, we employ a rule-based model to generate trajectories based on augmented scenes; thus enlarging the trajectories beyond the collected real ones. To foster the learning of general representations within this augmented dataset, we comprehensively explore the different pre-training strategies, including extending the concept of a Masked AutoEncoder (MAE) for trajectory forecasting. Extensive experiments demonstrate the effectiveness of our data expansion and pre-training strategies, which outperform the baseline prediction model by large margins, e.g. 5.04%, 3.84% and 8.30% in terms of $MR_6$, $minADE_6$ and $minFDE_6$.

HD2Reg: Hierarchical Descriptors and Detectors for Point Cloud Registration

Feature Descriptors and Detectors are two main components of feature-based point cloud registration. However, little attention has been drawn to the explicit representation of local and global semantics in the learning of descriptors and detectors. In this paper, we present a framework that explicitly extracts dual-level descriptors and detectors and performs coarse-to-fine matching with them. First, to explicitly learn local and global semantics, we propose a hierarchical contrastive learning strategy, training the robust matching ability of high-level descriptors, and refining the local feature space using low-level descriptors. Furthermore, we propose to learn dual-level saliency maps that extract two groups of keypoints in two different senses. To overcome the weak supervision of binary matchability labels, we propose a ranking strategy to label the significance ranking of keypoints, and thus provide more fine-grained supervision signals. Finally, we propose a global-to-local matching scheme to obtain robust and accurate correspondences by leveraging the complementary dual-level features.Quantitative experiments on 3DMatch and KITTI odometry datasets show that our method achieves robust and accurate point cloud registration and outperforms recent keypoint-based methods.