We introduce STSBench, a scenario-based framework to benchmark the holistic understanding of vision-language models (VLMs) for autonomous driving. The framework automatically mines pre-defined traffic scenarios from any dataset using ground-truth annotations, provides an intuitive user interface for efficient human verification, and generates multiple-choice questions for model evaluation. Applied to the NuScenes dataset, we present STSnu, the first benchmark that evaluates the spatio-temporal reasoning capabilities of VLMs based on comprehensive 3D perception. Existing benchmarks typically target off-the-shelf or fine-tuned VLMs for images or videos from a single viewpoint and focus on semantic tasks such as object recognition, dense captioning, risk assessment, or scene understanding. In contrast, STSnu evaluates driving expert VLMs for end-to-end driving, operating on videos from multi-view cameras or LiDAR. It specifically assesses their ability to reason about both ego-vehicle actions and complex interactions among traffic participants, a crucial capability for autonomous vehicles. The benchmark features 43 diverse scenarios spanning multiple views and frames, resulting in 971 human-verified multiple-choice questions. A thorough evaluation uncovers critical shortcomings in existing models' ability to reason about fundamental traffic dynamics in complex environments. These findings highlight the urgent need for architectural advances that explicitly model spatio-temporal reasoning. By addressing a core gap in spatio-temporal evaluation, STSBench enables the development of more robust and explainable VLMs for autonomous driving.
Remarkable progress in 2D Vision-Language Models (VLMs) has spurred interest in extending them to 3D settings for tasks like 3D Question Answering, Dense Captioning, and Visual Grounding. Unlike 2D VLMs that typically process images through an image encoder, 3D scenes, with their intricate spatial structures, allow for diverse model architectures. Based on their encoder design, this paper categorizes recent 3D VLMs into 3D object-centric, 2D image-based, and 3D scene-centric approaches. Despite the architectural similarity of 3D scene-centric VLMs to their 2D counterparts, they have exhibited comparatively lower performance compared with the latest 3D object-centric and 2D image-based approaches. To understand this gap, we conduct an in-depth analysis, revealing that 3D scene-centric VLMs show limited reliance on the 3D scene encoder, and the pre-train stage appears less effective than in 2D VLMs. Furthermore, we observe that data scaling benefits are less pronounced on larger datasets. Our investigation suggests that while these models possess cross-modal alignment capabilities, they tend to over-rely on linguistic cues and overfit to frequent answer distributions, thereby diminishing the effective utilization of the 3D encoder. To address these limitations and encourage genuine 3D scene understanding, we introduce a novel 3D Relevance Discrimination QA dataset designed to disrupt shortcut learning and improve 3D understanding. Our findings highlight the need for advanced evaluation and improved strategies for better 3D understanding in 3D VLMs.
Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as unsegmented streams, which obscures fine-grained event boundaries and limits the modeling of causal dependencies. We propose TEMPURA (Temporal Event Masked Prediction and Understanding for Reasoning in Action), a two-stage training framework that enhances video temporal understanding. TEMPURA first applies masked event prediction reasoning to reconstruct missing events and generate step-by-step causal explanations from dense event annotations, drawing inspiration from effective infilling techniques. TEMPURA then learns to perform video segmentation and dense captioning to decompose videos into non-overlapping events with detailed, timestamp-aligned descriptions. We train TEMPURA on VER, a large-scale dataset curated by us that comprises 1M training instances and 500K videos with temporally aligned event descriptions and structured reasoning steps. Experiments on temporal grounding and highlight detection benchmarks demonstrate that TEMPURA outperforms strong baseline models, confirming that integrating causal reasoning with fine-grained temporal segmentation leads to improved video understanding.
Multimodal Large Language Models (MLLMs) have made significant progress in tasks such as image captioning and question answering. However, while these models can generate realistic captions, they often struggle with providing precise instructions, particularly when it comes to localizing and disambiguating objects in complex 3D environments. This capability is critical as MLLMs become more integrated with collaborative robotic systems. In scenarios where a target object is surrounded by similar objects (distractors), robots must deliver clear, spatially-aware instructions to guide humans effectively. We refer to this challenge as contextual object localization and disambiguation, which imposes stricter constraints than conventional 3D dense captioning, especially regarding ensuring target exclusivity. In response, we propose simple yet effective techniques to enhance the model's ability to localize and disambiguate target objects. Our approach not only achieves state-of-the-art performance on conventional metrics that evaluate sentence similarity, but also demonstrates improved 3D spatial understanding through 3D visual grounding model.
3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms. Therefore, these methods focus on a limited range of reasoning sub-tasks and rely heavily on the hand-crafted modules and auxiliary losses. This highlights the need for a simpler, unified and general-purpose model. In this paper, we leverage the inherent connection between 3D scene graphs and natural language, proposing a 3D scene graph-guided vision-language pre-training (VLP) framework. Our approach utilizes modality encoders, graph convolutional layers and cross-attention layers to learn universal representations that adapt to a variety of 3D VL reasoning tasks, thereby eliminating the need for task-specific designs. The pre-training objectives include: 1) Scene graph-guided contrastive learning, which leverages the strong correlation between 3D scene graphs and natural language to align 3D objects with textual features at various fine-grained levels; and 2) Masked modality learning, which uses cross-modality information to reconstruct masked words and 3D objects. Instead of directly reconstructing the 3D point clouds of masked objects, we use position clues to predict their semantic categories. Extensive experiments demonstrate that our pre-training model, when fine-tuned on several downstream tasks, achieves performance comparable to or better than existing methods in tasks such as 3D visual grounding, 3D dense captioning, and 3D question answering.
Enabling Large Language Models (LLMs) to understand the 3D physical world is an emerging yet challenging research direction. Current strategies for processing point clouds typically downsample the scene or divide it into smaller parts for separate analysis. However, both approaches risk losing key local details or global contextual information. In this paper, we introduce PerLA, a 3D language assistant designed to be more perceptive to both details and context, making visual representations more informative for the LLM. PerLA captures high-resolution (local) details in parallel from different point cloud areas and integrates them with (global) context obtained from a lower-resolution whole point cloud. We present a novel algorithm that preserves point cloud locality through the Hilbert curve and effectively aggregates local-to-global information via cross-attention and a graph neural network. Lastly, we introduce a novel loss for local representation consensus to promote training stability. PerLA outperforms state-of-the-art 3D language assistants, with gains of up to +1.34 CiDEr on ScanQA for question answering, and +4.22 on ScanRefer and +3.88 on Nr3D for dense captioning.\url{https://gfmei.github.io/PerLA/}
The comic domain is rapidly advancing with the development of single- and multi-page analysis and synthesis models. Recent benchmarks and datasets have been introduced to support and assess models' capabilities in tasks such as detection (panels, characters, text), linking (character re-identification and speaker identification), and analysis of comic elements (e.g., dialog transcription). However, to provide a comprehensive understanding of the storyline, a model must not only extract elements but also understand their relationships and generate highly informative captions. In this work, we propose a pipeline that leverages Vision-Language Models (VLMs) to obtain dense, grounded captions. To construct our pipeline, we introduce an attribute-retaining metric that assesses whether all important attributes are identified in the caption. Additionally, we created a densely annotated test set to fairly evaluate open-source VLMs and select the best captioning model according to our metric. Our pipeline generates dense captions with bounding boxes that are quantitatively and qualitatively superior to those produced by specifically trained models, without requiring any additional training. Using this pipeline, we annotated over 2 million panels across 13,000 books, which will be available on the project page https://github.com/emanuelevivoli/ComiCap.
End-to-end architectures in autonomous driving (AD) face a significant challenge in interpretability, impeding human-AI trust. Human-friendly natural language has been explored for tasks such as driving explanation and 3D captioning. However, previous works primarily focused on the paradigm of declarative interpretability, where the natural language interpretations are not grounded in the intermediate outputs of AD systems, making the interpretations only declarative. In contrast, aligned interpretability establishes a connection between language and the intermediate outputs of AD systems. Here we introduce Hint-AD, an integrated AD-language system that generates language aligned with the holistic perception-prediction-planning outputs of the AD model. By incorporating the intermediate outputs and a holistic token mixer sub-network for effective feature adaptation, Hint-AD achieves desirable accuracy, achieving state-of-the-art results in driving language tasks including driving explanation, 3D dense captioning, and command prediction. To facilitate further study on driving explanation task on nuScenes, we also introduce a human-labeled dataset, Nu-X. Codes, dataset, and models will be publicly available.
We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion model (LDM) architecture and introduce a video variational autoencoder (VidVAE). VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens and the computational demands associated with generating long-sequence videos. To further address the computational costs, we propose a divide-and-merge strategy that maintains temporal consistency across video segments. Our Diffusion Transformer (DiT) model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios. We have devised a data processing pipeline from the very beginning and collected over 13M high-quality video-text pairs. The pipeline includes multiple steps such as clipping, text detection, motion estimation, aesthetics scoring, and dense captioning based on our in-house video-LLM model. Training the VidVAE and DiT models required approximately 40 and 642 H100 days, respectively. Our model supports over 14-second 720p video generation in an end-to-end way and demonstrates competitive performance against state-of-the-art T2V models.
3D dense captioning is a task to localize objects in a 3D scene and generate descriptive sentences for each object. Recent approaches in 3D dense captioning have adopted transformer encoder-decoder frameworks from object detection to build an end-to-end pipeline without hand-crafted components. However, these approaches struggle with contradicting objectives where a single query attention has to simultaneously view both the tightly localized object regions and contextual environment. To overcome this challenge, we introduce SIA (See-It-All), a transformer pipeline that engages in 3D dense captioning with a novel paradigm called late aggregation. SIA simultaneously decodes two sets of queries-context query and instance query. The instance query focuses on localization and object attribute descriptions, while the context query versatilely captures the region-of-interest of relationships between multiple objects or with the global scene, then aggregated afterwards (i.e., late aggregation) via simple distance-based measures. To further enhance the quality of contextualized caption generation, we design a novel aggregator to generate a fully informed caption based on the surrounding context, the global environment, and object instances. Extensive experiments on two of the most widely-used 3D dense captioning datasets demonstrate that our proposed method achieves a significant improvement over prior methods.
3D dense captioning is a task involving the localization of objects and the generation of descriptions for each object in a 3D scene. Recent approaches have attempted to incorporate contextual information by modeling relationships with object pairs or aggregating the nearest neighbor features of an object. However, the contextual information constructed in these scenarios is limited in two aspects: first, objects have multiple positional relationships that exist across the entire global scene, not only near the object itself. Second, it faces with contradicting objectives--where localization and attribute descriptions are generated better with tight localization, while descriptions involving global positional relations are generated better with contextualized features of the global scene. To overcome this challenge, we introduce BiCA, a transformer encoder-decoder pipeline that engages in 3D dense captioning for each object with Bi-directional Contextual Attention. Leveraging parallelly decoded instance queries for objects and context queries for non-object contexts, BiCA generates object-aware contexts, where the contexts relevant to each object is summarized, and context-aware objects, where the objects relevant to the summarized object-aware contexts are aggregated. This extension relieves previous methods from the contradicting objectives, enhancing both localization performance and enabling the aggregation of contextual features throughout the global scene; thus improving caption generation performance simultaneously. Extensive experiments on two of the most widely-used 3D dense captioning datasets demonstrate that our proposed method achieves a significant improvement over prior methods.
This research introduces the first multimodal approach for pavement condition assessment, providing both quantitative Pavement Condition Index (PCI) predictions and qualitative descriptions. We introduce PaveCap, a novel framework for automated pavement condition assessment. The framework consists of two main parts: a Single-Shot PCI Estimation Network and a Dense Captioning Network. The PCI Estimation Network uses YOLOv8 for object detection, the Segment Anything Model (SAM) for zero-shot segmentation, and a four-layer convolutional neural network to predict PCI. The Dense Captioning Network uses a YOLOv8 backbone, a Transformer encoder-decoder architecture, and a convolutional feed-forward module to generate detailed descriptions of pavement conditions. To train and evaluate these networks, we developed a pavement dataset with bounding box annotations, textual annotations, and PCI values. The results of our PCI Estimation Network showed a strong positive correlation (0.70) between predicted and actual PCIs, demonstrating its effectiveness in automating condition assessment. Also, the Dense Captioning Network produced accurate pavement condition descriptions, evidenced by high BLEU (0.7445), GLEU (0.5893), and METEOR (0.7252) scores. Additionally, the dense captioning model handled complex scenarios well, even correcting some errors in the ground truth data. The framework developed here can greatly improve infrastructure management and decision18 making in pavement maintenance.
Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop models with compositional understanding capabilities, this is not reflected yet in existing datasets which, for the most part, still use plain text to describe images. In this work, we propose a new annotation strategy, graph-based captioning (GBC) that describes an image using a labelled graph structure, with nodes of various types. The nodes in GBC are created using, in a first stage, object detection and dense captioning tools nested recursively to uncover and describe entity nodes, further linked together in a second stage by highlighting, using new types of nodes, compositions and relations among entities. Since all GBC nodes hold plain text descriptions, GBC retains the flexibility found in natural language, but can also encode hierarchical information in its edges. We demonstrate that GBC can be produced automatically, using off-the-shelf multimodal LLMs and open-vocabulary detection models, by building a new dataset, GBC10M, gathering GBC annotations for about 10M images of the CC12M dataset. We use GBC10M to showcase the wealth of node captions uncovered by GBC, as measured with CLIP training. We show that using GBC nodes' annotations -- notably those stored in composition and relation nodes -- results in significant performance boost on downstream models when compared to other dataset formats. To further explore the opportunities provided by GBC, we also propose a new attention mechanism that can leverage the entire GBC graph, with encouraging experimental results that show the extra benefits of incorporating the graph structure. Our datasets are released at \url{https://huggingface.co/graph-based-captions}.
3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, and room levels, which has the advantages of diverse scene data, rich textual descriptions, multi-grained 3D-text associations, and low collection cost. Utilizing the rich annotations in SynVL3D, we pre-train a simple and unified Transformer for aligning 3D and language with multi-grained pretraining tasks. Moreover, we propose a synthetic-to-real domain adaptation in downstream task fine-tuning process to address the domain shift. Through extensive experiments, we verify the effectiveness of our model design by achieving state-of-the-art performance on downstream tasks including visual grounding, dense captioning, and question answering.
The state of an object reflects its current status or condition and is important for a robot's task planning and manipulation. However, detecting an object's state and generating a state-sensitive plan for robots is challenging. Recently, pre-trained Large Language Models (LLMs) and Vision-Language Models (VLMs) have shown impressive capabilities in generating plans. However, to the best of our knowledge, there is hardly any investigation on whether LLMs or VLMs can also generate object state-sensitive plans. To study this, we introduce an Object State-Sensitive Agent (OSSA), a task-planning agent empowered by pre-trained neural networks. We propose two methods for OSSA: (i) a modular model consisting of a pre-trained vision processing module (dense captioning model, DCM) and a natural language processing model (LLM), and (ii) a monolithic model consisting only of a VLM. To quantitatively evaluate the performances of the two methods, we use tabletop scenarios where the task is to clear the table. We contribute a multimodal benchmark dataset that takes object states into consideration. Our results show that both methods can be used for object state-sensitive tasks, but the monolithic approach outperforms the modular approach. The code for OSSA is available at https://github.com/Xiao-wen-Sun/OSSA
Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal models (3D LMMs) to consolidate various 3D vision tasks within a unified generative framework. The model uses scene referent tokens as special noun phrases to reference 3D scenes, enabling it to handle sequences that interleave 3D and textual data. Per-task instruction-following templates are employed to ensure natural and diversity in translating 3D vision tasks into language formats. To facilitate the use of referent tokens in subsequent language modeling, we provide a large-scale, automatically curated grounded scene-text dataset with over 1 million phrase-to-region correspondences and introduce Contrastive Language-Scene Pre-training (CLASP) to perform phrase-level scene-text alignment using this data. Our comprehensive evaluation covers open-ended tasks like dense captioning and 3D question answering, alongside close-ended tasks such as object detection and language grounding. Experiments across multiple 3D benchmarks reveal the leading performance and the broad applicability of Grounded 3D-LLM. Code and datasets are available at the https://groundedscenellm.github.io/grounded_3d-llm.github.io.
Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources, which hinders the progress of video-language models. This paper investigates a straight-forward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for dense video understanding. Our preliminary experiments reveal that directly fine-tuning pre-trained image-language models with multiple frames as inputs on video datasets leads to performance saturation or even a drop. Our further investigation reveals that it is largely attributed to the bias of learned high-norm visual features. Motivated by this finding, we propose a simple but effective pooling strategy to smooth the feature distribution along the temporal dimension and thus reduce the dominant impacts from the extreme features. The new model is termed Pooling LLaVA, or PLLaVA in short. PLLaVA achieves new state-of-the-art performance on modern benchmark datasets for both video question-answer and captioning tasks. Notably, on the recent popular VideoChatGPT benchmark, PLLaVA achieves a score of 3.48 out of 5 on average of five evaluated dimensions, exceeding the previous SOTA results from GPT4V (IG-VLM) by 9%. On the latest multi-choice benchmark MVBench, PLLaVA achieves 58.1% accuracy on average across 20 sub-tasks, 14.5% higher than GPT4V (IG-VLM). Code is available at https://pllava.github.io/
3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in various 3D applications, which require both shared and complementary information in localization and visual-language relationships. Therefore, existing approaches adopt the two-stage "detect-then-describe/discriminate" pipeline, which relies heavily on the performance of the detector, resulting in suboptimal performance. Inspired by DETR, we propose a unified framework, 3DGCTR, to jointly solve these two distinct but closely related tasks in an end-to-end fashion. The key idea is to reconsider the prompt-based localization ability of the 3DVG model. In this way, the 3DVG model with a well-designed prompt as input can assist the 3DDC task by extracting localization information from the prompt. In terms of implementation, we integrate a Lightweight Caption Head into the existing 3DVG network with a Caption Text Prompt as a connection, effectively harnessing the existing 3DVG model's inherent localization capacity, thereby boosting 3DDC capability. This integration facilitates simultaneous multi-task training on both tasks, mutually enhancing their performance. Extensive experimental results demonstrate the effectiveness of this approach. Specifically, on the ScanRefer dataset, 3DGCTR surpasses the state-of-the-art 3DDC method by 4.3% in [email omitted] in MLE training and improves upon the SOTA 3DVG method by 3.16% in [email omitted]. The codes are at https://github.com/Leon1207/3DGCTR.
Existing open-vocabulary object detectors typically require a predefined set of categories from users, significantly confining their application scenarios. In this paper, we introduce DetCLIPv3, a high-performing detector that excels not only at both open-vocabulary object detection, but also generating hierarchical labels for detected objects. DetCLIPv3 is characterized by three core designs: 1. Versatile model architecture: we derive a robust open-set detection framework which is further empowered with generation ability via the integration of a caption head. 2. High information density data: we develop an auto-annotation pipeline leveraging visual large language model to refine captions for large-scale image-text pairs, providing rich, multi-granular object labels to enhance the training. 3. Efficient training strategy: we employ a pre-training stage with low-resolution inputs that enables the object captioner to efficiently learn a broad spectrum of visual concepts from extensive image-text paired data. This is followed by a fine-tuning stage that leverages a small number of high-resolution samples to further enhance detection performance. With these effective designs, DetCLIPv3 demonstrates superior open-vocabulary detection performance, \eg, our Swin-T backbone model achieves a notable 47.0 zero-shot fixed AP on the LVIS minival benchmark, outperforming GLIPv2, GroundingDINO, and DetCLIPv2 by 18.0/19.6/6.6 AP, respectively. DetCLIPv3 also achieves a state-of-the-art 19.7 AP in dense captioning task on VG dataset, showcasing its strong generative capability.
3D dense captioning stands as a cornerstone in achieving a comprehensive understanding of 3D scenes through natural language. It has recently witnessed remarkable achievements, particularly in indoor settings. However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the domain gap between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the lack of data with comprehensive box-caption pair annotations specifically tailored for outdoor scenes. To this end, we introduce the new task of outdoor 3D dense captioning. As input, we assume a LiDAR point cloud and a set of RGB images captured by the panoramic camera rig. The expected output is a set of object boxes with captions. To tackle this task, we propose the TOD3Cap network, which leverages the BEV representation to generate object box proposals and integrates Relation Q-Former with LLaMA-Adapter to generate rich captions for these objects. We also introduce the TOD3Cap dataset, the largest one to our knowledge for 3D dense captioning in outdoor scenes, which contains 2.3M descriptions of 64.3K outdoor objects from 850 scenes. Notably, our TOD3Cap network can effectively localize and caption 3D objects in outdoor scenes, which outperforms baseline methods by a significant margin (+9.6 [email omitted]). Code, data, and models are publicly available at https://github.com/jxbbb/TOD3Cap.