Non-rigid point cloud registration is a critical challenge in 3D scene understanding, particularly in surgical navigation. Although existing methods achieve excellent performance when trained on large-scale, high-quality datasets, these datasets are prohibitively expensive to collect and annotate, e.g., organ data in authentic medical scenarios. With insufficient training samples and data noise, existing methods degrade significantly since non-rigid patterns are more flexible and complicated than rigid ones, and the distributions across samples are more distinct, leading to higher difficulty in representation learning with few data. In this work, we aim to deal with this challenging few-shot non-rigid point cloud registration problem. Based on the observation that complex non-rigid transformation patterns can be decomposed into rigid and small non-rigid transformations, we propose a novel and effective framework, UniRiT. UniRiT adopts a two-step registration strategy that first aligns the centroids of the source and target point clouds and then refines the registration with non-rigid transformations, thereby significantly reducing the problem complexity. To validate the performance of UniRiT on real-world datasets, we introduce a new dataset, MedMatch3D, which consists of real human organs and exhibits high variability in sample distribution. We further establish a new challenging benchmark for few-shot non-rigid registration. Extensive empirical results demonstrate that UniRiT achieves state-of-the-art performance on MedMatch3D, improving the existing best approach by 94.22%.
End-to-end autonomous driving demonstrates strong planning capabilities with large-scale data but still struggles in complex, rare scenarios due to limited commonsense. In contrast, Large Vision-Language Models (LVLMs) excel in scene understanding and reasoning. The path forward lies in merging the strengths of both approaches. Previous methods using LVLMs to predict trajectories or control signals yield suboptimal results, as LVLMs are not well-suited for precise numerical predictions. This paper presents Senna, an autonomous driving system combining an LVLM (Senna-VLM) with an end-to-end model (Senna-E2E). Senna decouples high-level planning from low-level trajectory prediction. Senna-VLM generates planning decisions in natural language, while Senna-E2E predicts precise trajectories. Senna-VLM utilizes a multi-image encoding approach and multi-view prompts for efficient scene understanding. Besides, we introduce planning-oriented QAs alongside a three-stage training strategy, which enhances Senna-VLM's planning performance while preserving commonsense. Extensive experiments on two datasets show that Senna achieves state-of-the-art planning performance. Notably, with pre-training on a large-scale dataset DriveX and fine-tuning on nuScenes, Senna significantly reduces average planning error by 27.12% and collision rate by 33.33% over model without pre-training. We believe Senna's cross-scenario generalization and transferability are essential for achieving fully autonomous driving. Code and models will be released at https://github.com/hustvl/Senna.
Purpose: Surgical phase recognition (SPR) is an integral component of surgical data science, enabling high-level surgical analysis. End-to-end trained neural networks that predict surgical phase directly from videos have shown excellent performance on benchmarks. However, these models struggle with robustness due to non-causal associations in the training set, resulting in poor generalizability. Our goal is to improve model robustness to variations in the surgical videos by leveraging the digital twin (DT) paradigm -- an intermediary layer to separate high-level analysis (SPR) from low-level processing (geometric understanding). This approach takes advantage of the recent vision foundation models that ensure reliable low-level scene understanding to craft DT-based scene representations that support various high-level tasks. Methods: We present a DT-based framework for SPR from videos. The framework employs vision foundation models to extract representations. We embed the representation in place of raw video inputs in the state-of-the-art Surgformer model. The framework is trained on the Cholec80 dataset and evaluated on out-of-distribution (OOD) and corrupted test samples. Results: Contrary to the vulnerability of the baseline model, our framework demonstrates strong robustness on both OOD and corrupted samples, with a video-level accuracy of 51.1 on the challenging CRCD dataset, 96.0 on an internal robotics training dataset, and 64.4 on a highly corrupted Cholec80 test set. Conclusion: Our findings lend support to the thesis that DT-based scene representations are effective in enhancing model robustness. Future work will seek to improve the feature informativeness, automate feature extraction, and incorporate interpretability for a more comprehensive framework.
Surgical scene segmentation is a fundamental task for robotic-assisted laparoscopic surgery understanding. It often contains various anatomical structures and surgical instruments, where similar local textures and fine-grained structures make the segmentation a difficult task. Vision-specific transformer method is a promising way for surgical scene understanding. However, there are still two main challenges. Firstly, the absence of inner-patch information fusion leads to poor segmentation performance. Secondly, the specific characteristics of anatomy and instruments are not specifically modeled. To tackle the above challenges, we propose a novel Transformer-based framework with an Asymmetric Feature Enhancement module (TAFE), which enhances local information and then actively fuses the improved feature pyramid into the embeddings from transformer encoders by a multi-scale interaction attention strategy. The proposed method outperforms the SOTA methods in several different surgical segmentation tasks and additionally proves its ability of fine-grained structure recognition. Code is available at https://github.com/cyuan-sjtu/ViT-asym.
Generating detailed descriptions from multiple cameras and viewpoints is challenging due to the complex and inconsistent nature of visual data. In this paper, we introduce PerspectiveNet, a lightweight yet efficient model for generating long descriptions across multiple camera views. Our approach utilizes a vision encoder, a compact connector module to convert visual features into a fixed-size tensor, and large language models (LLMs) to harness the strong natural language generation capabilities of LLMs. The connector module is designed with three main goals: mapping visual features onto LLM embeddings, emphasizing key information needed for description generation, and producing a fixed-size feature matrix. Additionally, we augment our solution with a secondary task, the correct frame sequence detection, enabling the model to search for the correct sequence of frames to generate descriptions. Finally, we integrate the connector module, the secondary task, the LLM, and a visual feature extraction model into a single architecture, which is trained for the Traffic Safety Description and Analysis task. This task requires generating detailed, fine-grained descriptions of events from multiple cameras and viewpoints. The resulting model is lightweight, ensuring efficient training and inference, while remaining highly effective.
Multi-modal fusion has played a vital role in multi-modal scene understanding. Most existing methods focus on cross-modal fusion involving two modalities, often overlooking more complex multi-modal fusion, which is essential for real-world applications like autonomous driving, where visible, depth, event, LiDAR, etc., are used. Besides, few attempts for multi-modal fusion, \emph{e.g.}, simple concatenation, cross-modal attention, and token selection, cannot well dig into the intrinsic shared and specific details of multiple modalities. To tackle the challenge, in this paper, we propose a Part-Whole Relational Fusion (PWRF) framework. For the first time, this framework treats multi-modal fusion as part-whole relational fusion. It routes multiple individual part-level modalities to a fused whole-level modality using the part-whole relational routing ability of Capsule Networks (CapsNets). Through this part-whole routing, our PWRF generates modal-shared and modal-specific semantics from the whole-level modal capsules and the routing coefficients, respectively. On top of that, modal-shared and modal-specific details can be employed to solve the issue of multi-modal scene understanding, including synthetic multi-modal segmentation and visible-depth-thermal salient object detection in this paper. Experiments on several datasets demonstrate the superiority of the proposed PWRF framework for multi-modal scene understanding. The source code has been released on https://github.com/liuyi1989/PWRF.
With the broader usage and highly successful development of Large Language Models (LLMs), there has been a growth of interest and demand for applying LLMs to autonomous driving technology. Driven by their natural language understanding and reasoning ability, LLMs have the potential to enhance various aspects of autonomous driving systems, from perception and scene understanding to language interaction and decision-making. In this paper, we first introduce the novel concept of designing LLMs for autonomous driving (LLM4AD). Then, we propose a comprehensive benchmark for evaluating the instruction-following abilities of LLM4AD in simulation. Furthermore, we conduct a series of experiments on real-world vehicle platforms, thoroughly evaluating the performance and potential of our LLM4AD systems. Finally, we envision the main challenges of LLM4AD, including latency, deployment, security and privacy, safety, trust and transparency, and personalization. Our research highlights the significant potential of LLMs to enhance various aspects of autonomous vehicle technology, from perception and scene understanding to language interaction and decision-making.
The performance of neural networks scales with both their size and the amount of data they have been trained on. This is shown in both language and image generation. However, this requires scaling-friendly network architectures as well as large-scale datasets. Even though scaling-friendly architectures like transformers have emerged for 3D vision tasks, the GPT-moment of 3D vision remains distant due to the lack of training data. In this paper, we introduce ARKit LabelMaker, the first large-scale, real-world 3D dataset with dense semantic annotations. Specifically, we complement ARKitScenes dataset with dense semantic annotations that are automatically generated at scale. To this end, we extend LabelMaker, a recent automatic annotation pipeline, to serve the needs of large-scale pre-training. This involves extending the pipeline with cutting-edge segmentation models as well as making it robust to the challenges of large-scale processing. Further, we push forward the state-of-the-art performance on ScanNet and ScanNet200 dataset with prevalent 3D semantic segmentation models, demonstrating the efficacy of our generated dataset.
3D visual grounding is crucial for robots, requiring integration of natural language and 3D scene understanding. Traditional methods depending on supervised learning with 3D point clouds are limited by scarce datasets. Recently zero-shot methods leveraging LLMs have been proposed to address the data issue. While effective, these methods only use object-centric information, limiting their ability to handle complex queries. In this work, we present VLM-Grounder, a novel framework using vision-language models (VLMs) for zero-shot 3D visual grounding based solely on 2D images. VLM-Grounder dynamically stitches image sequences, employs a grounding and feedback scheme to find the target object, and uses a multi-view ensemble projection to accurately estimate 3D bounding boxes. Experiments on ScanRefer and Nr3D datasets show VLM-Grounder outperforms previous zero-shot methods, achieving 51.6% [email omitted] on ScanRefer and 48.0% Acc on Nr3D, without relying on 3D geometry or object priors. Codes are available at https://github.com/OpenRobotLab/VLM-Grounder .
Foundation models have significantly enhanced 2D task performance, and recent works like Bridge3D have successfully applied these models to improve 3D scene understanding through knowledge distillation, marking considerable advancements. Nonetheless, challenges such as the misalignment between 2D and 3D representations and the persistent long-tail distribution in 3D datasets still restrict the effectiveness of knowledge distillation from 2D to 3D using foundation models. To tackle these issues, we introduce a novel SAM-guided tokenization method that seamlessly aligns 3D transformer structures with region-level knowledge distillation, replacing the traditional KNN-based tokenization techniques. Additionally, we implement a group-balanced re-weighting strategy to effectively address the long-tail problem in knowledge distillation. Furthermore, inspired by the recent success of masked feature prediction, our framework incorporates a two-stage masked token prediction process in which the student model predicts both the global embeddings and the token-wise local embeddings derived from the teacher models trained in the first stage. Our methodology has been validated across multiple datasets, including SUN RGB-D, ScanNet, and S3DIS, for tasks like 3D object detection and semantic segmentation. The results demonstrate significant improvements over current State-of-the-art self-supervised methods, establishing new benchmarks in this field.
3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Accurately reconstructing an object's complete 3D structure and texture has numerous applications in real-world scenarios, including robotic manipulation, grasping, 3D scene understanding, and AR/VR. Recent advancements in 3D object generation have introduced techniques that reconstruct an object's 3D shape and texture by optimizing the efficient representation of Gaussian Splatting, guided by pre-trained 2D or 3D diffusion models. However, a notable disparity exists between the training datasets of these models, leading to distinct differences in their outputs. While 2D models generate highly detailed visuals, they lack cross-view consistency in geometry and texture. In contrast, 3D models ensure consistency across different views but often result in overly smooth textures. We propose bridging the gap between 2D and 3D diffusion models to address this limitation by integrating a two-stage frequency-based distillation loss with Gaussian Splatting. Specifically, we leverage geometric priors in the low-frequency spectrum from a 3D diffusion model to maintain consistent geometry and use a 2D diffusion model to refine the fidelity and texture in the high-frequency spectrum of the generated 3D structure, resulting in more detailed and fine-grained outcomes. Our approach enhances geometric consistency and visual quality, outperforming the current SOTA. Additionally, we demonstrate the easy adaptability of our method for efficient object pose estimation and tracking.
In Autonomous Driving (AD) Perception, cyclists are considered safety-critical scene objects. Commonly used publicly-available AD datasets typically contain large amounts of car and vehicle object instances but a low number of cyclist instances, usually with limited appearance and pose diversity. This cyclist training data scarcity problem not only limits the generalization of deep-learning perception models for cyclist semantic segmentation, pose estimation, and cyclist crossing intention prediction, but also limits research on new cyclist-related tasks such as fine-grained cyclist pose estimation and spatio-temporal analysis under complex interactions between humans and articulated objects. To address this data scarcity problem, in this paper we propose a framework to generate synthetic dynamic 3D cyclist data assets that can be used to generate training data for different tasks. In our framework, we designed a methodology for creating a new part-based multi-view articulated synthetic 3D bicycle dataset that we call 3DArticBikes that we use to train a 3D Gaussian Splatting (3DGS)-based reconstruction and image rendering method. We then propose a parametric bicycle 3DGS composition model to assemble 8-DoF pose-controllable 3D bicycles. Finally, using dynamic information from cyclist videos, we build a complete synthetic dynamic 3D cyclist (rider pedaling a bicycle) by re-posing a selectable synthetic 3D person, while automatically placing the rider onto one of our new articulated 3D bicycles using a proposed 3D Keypoint optimization-based Inverse Kinematics pose refinement. We present both, qualitative and quantitative results where we compare our generated cyclists against those from a recent stable diffusion-based method.
Low-light image enhancement (LLIE) is essential for numerous computer vision tasks, including object detection, tracking, segmentation, and scene understanding. Despite substantial research on improving low-quality images captured in underexposed conditions, clear vision remains critical for autonomous vehicles, which often struggle with low-light scenarios, signifying the need for continuous research. However, paired datasets for LLIE are scarce, particularly for street scenes, limiting the development of robust LLIE methods. Despite using advanced transformers and/or diffusion-based models, current LLIE methods struggle in real-world low-light conditions and lack training on street-scene datasets, limiting their effectiveness for autonomous vehicles. To bridge these gaps, we introduce a new dataset LoLI-Street (Low-Light Images of Streets) with 33k paired low-light and well-exposed images from street scenes in developed cities, covering 19k object classes for object detection. LoLI-Street dataset also features 1,000 real low-light test images for testing LLIE models under real-life conditions. Furthermore, we propose a transformer and diffusion-based LLIE model named "TriFuse". Leveraging the LoLI-Street dataset, we train and evaluate our TriFuse and SOTA models to benchmark on our dataset. Comparing various models, our dataset's generalization feasibility is evident in testing across different mainstream datasets by significantly enhancing images and object detection for practical applications in autonomous driving and surveillance systems. The complete code and dataset is available on https://github.com/tanvirnwu/TriFuse.
Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context. Deep learning models often struggle to generalize to real-world images due to the limited size and diversity of training datasets. To address this, we introduce TICA, a novel framework that leverages light-intensity information during test-time adaptation to enhance shadow detection accuracy. TICA exploits the inherent inconsistencies in light intensity across shadow regions to guide the model toward a more consistent prediction. A basic encoder-decoder model is initially trained on a labeled dataset for shadow detection. Then, during the testing phase, the network is adjusted for each test sample by enforcing consistent intensity predictions between two augmented input image versions. This consistency training specifically targets both foreground and background intersection regions to identify shadow regions within images accurately for robust adaptation. Extensive evaluations on the ISTD and SBU shadow detection datasets reveal that TICA significantly demonstrates that TICA outperforms existing state-of-the-art methods, achieving superior results in balanced error rate (BER).
Recent advancements in 3D reconstruction methods and vision-language models have propelled the development of multi-modal 3D scene understanding, which has vital applications in robotics, autonomous driving, and virtual/augmented reality. However, current multi-modal scene understanding approaches have naively embedded semantic representations into 3D reconstruction methods without striking a balance between visual and language modalities, which leads to unsatisfying semantic rasterization of translucent or reflective objects, as well as over-fitting on color modality. To alleviate these limitations, we propose a solution that adequately handles the distinct visual and semantic modalities, i.e., a 3D vision-language Gaussian splatting model for scene understanding, to put emphasis on the representation learning of language modality. We propose a novel cross-modal rasterizer, using modality fusion along with a smoothed semantic indicator for enhancing semantic rasterization. We also employ a camera-view blending technique to improve semantic consistency between existing and synthesized views, thereby effectively mitigating over-fitting. Extensive experiments demonstrate that our method achieves state-of-the-art performance in open-vocabulary semantic segmentation, surpassing existing methods by a significant margin.
Visual scene understanding is a fundamental task in computer vision that aims to extract meaningful information from visual data. It traditionally involves disjoint and specialized algorithms for different tasks that are tailored for specific application scenarios. This can be cumbersome when designing complex systems that include processing of visual and semantic data extracted from visual scenes, which is even more noticeable nowadays with the influx of applications for virtual or augmented reality. When designing a system that employs automatic visual scene understanding to enable a precise and semantically coherent description of the underlying scene, which can be used to fuel a visualization component with 3D virtual synthesis, the lack of flexibility and unified frameworks become more prominent. To alleviate this issue and its inherent problems, we propose an architecture that addresses the challenges of visual scene understanding and description towards a 3D virtual synthesis that enables an adaptable, unified and coherent solution. Furthermore, we expose how our proposition can be of use into multiple application areas. Additionally, we also present a proof of concept system that employs our architecture to further prove its usability in practice.
Semantic segmentation is a critical technique for effective scene understanding. Traditional RGB-T semantic segmentation models often struggle to generalize across diverse scenarios due to their reliance on pretrained models and predefined categories. Recent advancements in Visual Language Models (VLMs) have facilitated a shift from closed-set to open-vocabulary semantic segmentation methods. However, these models face challenges in dealing with intricate scenes, primarily due to the heterogeneity between RGB and thermal modalities. To address this gap, we present Open-RGBT, a novel open-vocabulary RGB-T semantic segmentation model. Specifically, we obtain instance-level detection proposals by incorporating visual prompts to enhance category understanding. Additionally, we employ the CLIP model to assess image-text similarity, which helps correct semantic consistency and mitigates ambiguities in category identification. Empirical evaluations demonstrate that Open-RGBT achieves superior performance in diverse and challenging real-world scenarios, even in the wild, significantly advancing the field of RGB-T semantic segmentation.
Point cloud semantic segmentation, the process of classifying each point into predefined categories, is essential for 3D scene understanding. While image-based segmentation is widely adopted due to its maturity, methods relying solely on RGB information often suffer from degraded performance due to color inaccuracies. Recent advancements have incorporated additional features such as intensity and geometric information, yet RGB channels continue to negatively impact segmentation accuracy when errors in colorization occur. Despite this, previous studies have not rigorously quantified the effects of erroneous colorization on segmentation performance. In this paper, we propose a novel statistical approach to evaluate the impact of inaccurate RGB information on image-based point cloud segmentation. We categorize RGB inaccuracies into two types: incorrect color information and similar color information. Our results demonstrate that both types of color inaccuracies significantly degrade segmentation accuracy, with similar color errors particularly affecting the extraction of geometric features. These findings highlight the critical need to reassess the role of RGB information in point cloud segmentation and its implications for future algorithm design.
Integrating the 3D world into large language models (3D-based LLMs) has been a promising research direction for 3D scene understanding. However, current 3D-based LLMs fall short in situated understanding due to two key limitations: 1) existing 3D datasets are constructed from a global perspective of the 3D scenes and lack situated context. 2) the architectures of existing 3D-based LLMs lack explicit alignment between the spatial representations of 3D scenes and natural language, limiting their performance in tasks requiring precise spatial reasoning. We address these issues by introducing a scalable situated 3D dataset, named Spartun3D, that incorporates various situated spatial reasoning tasks. Furthermore, we propose Spartun3D-LLM, built on an existing 3D-based LLM but integrated with a novel situated spatial alignment module, aiming to enhance the alignment between 3D visual representations and their corresponding textual descriptions. Experimental results demonstrate that both our proposed dataset and alignment module significantly enhance the situated spatial understanding of 3D-based LLMs.
In recent years, 3D vision has become a crucial field within computer vision, powering a wide range of applications such as autonomous driving, robotics, augmented reality, and medical imaging. This field relies on accurate perception, understanding, and reconstruction of 3D scenes from 2D images or text data sources. Diffusion models, originally designed for 2D generative tasks, offer the potential for more flexible, probabilistic methods that can better capture the variability and uncertainty present in real-world 3D data. In this paper, we review the state-of-the-art methods that use diffusion models for 3D visual tasks, including but not limited to 3D object generation, shape completion, point-cloud reconstruction, and scene construction. We provide an in-depth discussion of the underlying mathematical principles of diffusion models, outlining their forward and reverse processes, as well as the various architectural advancements that enable these models to work with 3D datasets. We also discuss the key challenges in applying diffusion models to 3D vision, such as handling occlusions and varying point densities, and the computational demands of high-dimensional data. Finally, we discuss potential solutions, including improving computational efficiency, enhancing multimodal fusion, and exploring the use of large-scale pretraining for better generalization across 3D tasks. This paper serves as a foundation for future exploration and development in this rapidly evolving field.