Neural network performance scales with both model size and data volume, as shown in both language and image processing. This requires scaling-friendly architectures and large datasets. While transformers have been adapted for 3D vision, a ‘GPT-moment’ remains elusive due to limited training data. We introduce ARKit LabelMaker, a large-scale real-world 3D dataset with dense semantic annotation that is more than three times larger than prior largest dataset. Specifically, we extend ARKitScenes [4] with automatically generated dense 3D labels using an extended LabelMaker pipeline [37], tailored for large-scale pre-training. Training on our dataset improves accuracy across architectures, achieving state-of-the-art 3D semantic segmentation scores on ScanNet and ScanNet200, with notable gains on tail classes. Our code is available at labelmaker.org and our dataset at huggingface.

We introduce the task of predicting functional 3D scene graphs for real-world indoor environments from posed RGB-D images. Unlike traditional 3D scene graphs that focus on spatial relationships of objects, functional 3D scene graphs capture objects, interactive elements, and their functional relationships. Due to the lack of training data, we leverage foundation models, including visual language models (VLMs) and large language models (LLMs), to encode functional knowledge. We evaluate our approach on an extended SceneFun3D dataset and a newly collected dataset, FunGraph3D, both annotated with functional 3D scene graphs. Our method significantly outperforms adapted baselines, including Open3DSG and ConceptGraph, demonstrating its effectiveness in modeling complex scene functionalities. We also demonstrate downstream applications such as 3D question answering and robotic manipulation using functional 3D scene graphs. See our project page at https://openfungraph.github.io.

We present SuperDec, an approach for creating compact 3D scene representations via decomposition into superquadric primitives. While most recent works leverage geometric primitives to obtain photorealistic 3D scene representations, we propose to leverage them to obtain a compact yet expressive representation. We propose to solve the problem locally on individual objects and leverage the capabilities of instance segmentation methods to scale our solution to full 3D scenes. In doing that, we design a new architecture which efficiently decompose point clouds of arbitrary objects in a compact set of superquadrics. We train our architecture on ShapeNet and we prove its generalization capabilities on object instances extracted from the ScanNet++ dataset as well as on full Replica scenes. Finally, we show how a compact representation based on superquadrics can be useful for a diverse range of downstream applications, including robotic tasks and controllable visual content generation and editing.

The ability to predict collision-free future trajectories from egocentric observations is crucial in applications such as humanoid robotics, VR / AR, and assistive navigation. In this work, we introduce the challenging problem of predicting a sequence of future 6D head poses from an egocentric video. In particular, we predict both head translations and rotations to learn the active information-gathering behavior expressed through head-turning events. To solve this task, we propose a framework that reasons over temporally aggregated 3D latent features, which models the geometric and semantic constraints for both the static and dynamic parts of the environment. Motivated by the lack of training data in this space, we further contribute a data collection pipeline using the Project Aria glasses, and present a dataset collected through this approach. Our dataset, dubbed Aria Navigation Dataset (AND), consists of 4 hours of recording of users navigating in real-world scenarios. It includes diverse situations and navigation behaviors, providing a valuable resource for learning real-world egocentric navigation policies. Extensive experiments show that our model learns human-like navigation behaviors such as waiting / slowing down, rerouting, and looking around for traffic while generalizing to unseen environments. Check out our project webpage at https://sites.google.com/stanford.edu/lookout.

Current 3D layout estimation models are predominantly trained on synthetic datasets biased toward simplistic, single-floor scenes. This prevents them from generalizing to complex, multi-floor buildings, often forcing a per-floor processing approach that sacrifices global context. Few works have attempted to holistically address multi-floor layouts. In this work, we introduce HouseLayout3D, a real-world benchmark dataset, which highlights the limitations of existing research when handling expansive, architecturally complex spaces. Additionally, we propose MultiFloor3D, a baseline method leveraging recent advances in 3D reconstruction and 2D segmentation. Our approach significantly outperforms state-of-the-art methods on both our new and existing datasets. Remarkably, it does not require any layout-specific training.

Automating the expert-dependent and labor-intensive task of 3D scene synthesis would significantly benefit fields such as architectural design, robotics simulation, and virtual reality. Recent approaches to 3D scene synthesis often rely on the commonsense reasoning of large language models (LLMs) or strong visual priors from image generation models. However, current LLMs exhibit limited 3D spatial reasoning, undermining the realism and global coherence of synthesized scenes, while image-generation-based methods often constrain viewpoint control and introduce multi-view inconsistencies. In this work, we present Video Perception models for 3D Scene synthesis (VIPScene), a novel framework that exploits the encoded commonsense knowledge of the 3D physical world in video generation models to ensure coherent scene layouts and consistent object placements across views. VIPScene accepts both text and image prompts and seamlessly integrates video generation, feedforward 3D reconstruction, and open-vocabulary perception models to semantically and geometrically analyze each object in a scene. This enables flexible scene synthesis with high realism and structural consistency. For a more sufficient evaluation on coherence and plausibility, we further introduce First-Person View Score (FPVScore), utilizing a continuous first-person perspective to capitalize on the reasoning ability of multimodal large language models. Extensive experiments show that VIPScene significantly outperforms existing methods and generalizes well across diverse scenarios.

Reverse engineering 3D computer-aided design (CAD) models from images is an important task for many downstream applications including interactive editing, manufacturing, architecture, robotics, etc. The difficulty of the task lies in vast representational disparities between the CAD output and the image input. CAD models are precise, programmatic constructs that involves sequential operations combining discrete command structure with continuous attributes – making it challenging to learn and optimize in an end-to-end fashion. Concurrently, input images introduce inherent challenges such as photometric variability and sensor noise, complicating the reverse engineering process. In this work, we introduce a novel approach that conditionally factorizes the task into two sub-problems. First, we leverage vision-language foundation models (VLMs), a finetuned Llama3.2, to predict the global discrete base structure with semantic information. Second, we propose TrAssembler that conditioned on the discrete structure with semantics predicts the continuous attribute values. To support the training of our TrAssembler, we further constructed an annotated CAD dataset of common objects from ShapeNet. Putting all together, our approach and data demonstrate significant first steps towards CAD-ifying images in the wild. Code and data can be found in https://github.com/qq456cvb/Img2CAD.

The rise of 2D vision-language models (VLMs) has en-abled new possibilities for language-driven 3D scene understanding tasks. Existing works focus on indoor scenes, or autonomous driving scenarios and typically validate against a pre-defined set of semantic object classes. In this work, we analyze the capabilities of vision-language models for large-scale urban 3D scene understanding, and propose new applications of VLMs that directly operate on aerial 3D reconstructions of cities. In particular, we address higher-level 3D scene understanding tasks such as population den-sity, building age, property prices, crime rate, and noise pollution. Our analysis reveals surprising zero-shot and few-shot performance of VLMs in urban environments.

We propose an online 3D semantic segmentation method that incrementally reconstructs a 3D semantic map from a stream of RGB-D frames. Unlike offline methods, ours is directly applicable to scenarios with real-time constraints, such as robotics or mixed reality. To overcome the inherent challenges of online methods, we make two main contributions. First, to effectively extract information from the input RGB-D video stream, we jointly estimate geometry and semantic labels per frame in 3D. A key focus of our approach is to reason about semantic entities both in the 2D input and the local 3D domain to leverage differences in spatial context and network architectures. Our method predicts 2D features using an off-the-shelf segmentation network. The extracted 2D features are refined by a lightweight 3D network to enable reasoning about the local 3D structure. Second, to efficiently deal with an infinite stream of input RGB-D frames, a subsequent network serves as a temporal expert predicting the incremental scene updates by leveraging 2D, 3D, and past information in a learned manner. These updates are then integrated into a global scene representation. Using these main contributions, our method can enable scenarios with real-time constraints and can scale to arbitrary scene sizes by processing and updating the scene only in a local region defined by the new measurement. Our experiments demonstrate improved results compared to existing online methods that purely operate in local regions and show that complementary sources of information can boost the performance. We provide a thorough ablation study on the benefits of different architectural as well as algorithmic design decisions. Our method yields competitive results on the popular ScanNet benchmark and SceneNN dataset.

Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generate labels for RGB-D scans at equal (or better) level of accuracy than comparable manually annotated datasets such as ScanNet. Our approach is based on an ensemble of state-of-the-art segmentation models and 3D lifting through neural rendering. We demonstrate the effectiveness of our LabelMaker pipeline by generating significantly better labels for the ScanNet datasets and automatically labelling the previously unlabeled ARKitScenes dataset. Code and models are available at labelmaker.org labelmaker.org.

Existing 3D scene understanding methods are heavily focused on 3D semantic and instance segmentation. However, identifying objects and their parts only constitutes an intermediate step towards a more fine-grained goal, which is effectively interacting with the functional interactive elements (e.g., handles, knobs, buttons) in the scene to accomplish diverse tasks. To this end, we introduce SceneFun3D, a large-scale dataset with more than 14. Bk highly accurate interaction annotations for 710 high-resolution real-world 3D indoor scenes. We accompany the annotations with motion parameter information, describing how to interact with these elements, and a diverse set of natural language descriptions of tasks that involve manipulating them in the scene context. To showcase the value of our dataset, we introduce three novel tasks, namely functionality segmentation, task-driven affordance grounding and 3D motion estimation, and adapt existing state-of-the-art methods to tackle them. Our experiments show that solving these tasks in real 3D scenes remains challenging despite recent progress in closed-set and open-set 3D scene understanding methods.

Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segment classes from a pre-defined training set. More recently, first works on open-set segmentation in 3D scenes have appeared in the literature. These methods are heavily influenced by closed-set 3D convolutional approaches that process point clouds or polygon meshes. However, these 3D scene representations do not align well with the image-based nature of the visual-language models. Indeed, point cloud and 3D meshes typically have a lower resolution than images and the reconstructed 3D scene geometry might not project well to the underlying 2D image sequences used to compute pixel-aligned CLIP features. To address these challenges, we propose OpenNeRF which naturally operates on posed images and directly encodes the VLM features within the NeRF. This is similar in spirit to LERF, however our work shows that using pixel-wise VLM features (instead of global CLIP features) results in an overall less complex architecture without the need for additional DINO regularization. Our OpenNeRF further leverages NeRF’s ability to render novel views and extract open-set VLM features from areas that are not well observed in the initial posed images. For 3D point cloud segmentation on the Replica dataset, OpenNeRF outperforms recent open-vocabulary methods such as LERF and OpenScene by at least +4.9 mIoU.

During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point to an object (or the background), while the user corrects errors in the resulting segmentation and feeds them back into the model. The current best practice formulates the problem as binary classification and segments objects one at a time. The model expects the user to provide positive clicks to indicate regions wrongly assigned to the background and negative clicks on regions wrongly assigned to the object. Sequentially visiting objects is wasteful since it disregards synergies between objects: a positive click for a given object can, by definition, serve as a negative click for nearby objects. Moreover, a direct competition between adjacent objects can speed up the identification of their common boundary. We introduce AGILE3D, an efficient, attention-based model that (1) supports simultaneous segmentation of multiple 3D objects, (2) yields more accurate segmentation masks with fewer user clicks, and (3) offers faster inference. Our core idea is to encode user clicks as spatial-temporal queries and enable explicit interactions between click queries as well as between them and the 3D scene through a click attention module. Every time new clicks are added, we only need to run a lightweight decoder that produces updated segmentation masks. In experiments with four different 3D point cloud datasets, AGILE3D sets a new state-of-the-art. Moreover, we also verify its practicality in real-world setups with real user studies. Project page: https://ywyue.github.io/AGILE3D.

Accurate grasping is the key to several robotic tasks including assembly and household robotics. Executing a successful grasp in a cluttered environment requires multiple levels of scene understanding: First, the robot needs to analyze the geometric properties of individual objects to find feasible grasps. These grasps need to be compliant with the local object geometry. Second, for each proposed grasp, the robot needs to reason about the interactions with other objects in the scene. Finally, the robot must compute a collision-free grasp trajectory while taking into account the geometry of the target object. Most grasp detection algorithms directly predict grasp poses in a monolithic fashion, which does not capture the composability of the environment. In this paper, we introduce an end-to-end architecture for object-centric grasping. The method uses pointcloud data from a single arbitrary viewing direction as an input and generates an instance-centric representation for each partially observed object in the scene. This representation is further used for object reconstruction and grasp detection in cluttered table-top scenes. We show the effectiveness of the proposed method by extensively evaluating it against state-of-the-art methods on synthetic datasets, indicating superior performance for grasping and reconstruction. Additionally, we demonstrate real-world applicability by decluttering scenes with varying numbers of objects. Videos and Code icgraspnet.github.io.

We address 2D floorplan reconstruction from 3D scans. Existing approaches typically employ heuristically designed multi-stage pipelines. Instead, we formulate floor-plan reconstruction as a single-stage structured prediction task: find a variablesize set of polygons, which in turn are variable-length sequences of ordered vertices. To solve it we develop a novel Transformer architecture that generates polygons of multiple rooms in parallel, in a holistic manner without hand-crafted intermediate stages. The model features two-level queries for polygons and corners, and includes polygon matching to make the network end-to-end trainable. Our method achieves a new state-of-the-art for two challenging datasets, Structured3D and SceneCAD, along with significantly faster inference than previous methods. Moreover, it can readily be extended to predict additional information, i.e., semantic room types and architectural elements like doors and windows. Our code and models are available at: https://github.com/ywyue/RoomFormer.

Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3D human semantic segmentation, instance segmentation and multi-human body-part segmentation. Few works have attempted to directly segment humans in cluttered 3D scenes, which is largely due to the lack of annotated training data of humans interacting with 3D scenes. We address this challenge and propose a framework for generating training data of synthetic humans interacting with real 3D scenes. Furthermore, we propose a novel transformer-based model, Human3D, which is the first end-to-end model for segmenting multiple human instances and their body-parts in a unified manner. The key advantage of our synthetic data generation framework is its ability to generate diverse and realistic human-scene interactions, with highly accurate ground truth. Our experiments show that pre-training on synthetic data improves performance on a wide variety of 3D human segmentation tasks. Finally, we demonstrate that Human3D outperforms even task-specific state-of-the-art 3D segmentation methods.

Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on the successes of recent Transformer-based methods for object detection and image segmentation, we propose the first Transformer-based approach for 3D semantic instance segmentation. We show that we can leverage generic Transformer building blocks to directly predict instance masks from 3D point clouds. In our model - called Mask3D - each object instance is represented as an instance query. Using Transformer decoders, the instance queries are learned by iteratively attending to point cloud features at multiple scales. Combined with point features, the instance queries directly yield all instance masks in parallel. Mask3D has several advantages over current state-of-the-art approaches, since it neither relies on (1) voting schemes which require hand-selected geometric properties (such as centers) nor (2) geometric grouping mechanisms requiring manually-tuned hyper-parameters (e.g. radii) and (3) enables a loss that directly optimizes instance masks. Mask3D sets a new state-of-the-art on ScanNet test (+6.2mAP), S3DIS 6-fold (+10.1 mAP), STPLS3D (+11.2 mAP) and ScanNet200 test (+12.4 mAP).

We introduce the task of open-vocabulary 3D instance segmentation. Current approaches for 3D instance segmentation can typically only recognize object categories from a pre-defined closed set of classes that are annotated in the training datasets. This results in important limitations for real-world applications where one might need to perform tasks guided by novel, open-vocabulary queries related to a wide variety of objects. Recently, open-vocabulary 3D scene understanding methods have emerged to address this problem by learning queryable features for each point in the scene. While such a representation can be directly employed to perform semantic segmentation, existing methods cannot separate multiple object instances. In this work, we address this limitation, and propose OpenMask3D, which is a zero-shot approach for open-vocabulary 3D instance segmentation. Guided by predicted class-agnostic 3D instance masks, our model aggregates per-mask features via multi-view fusion of CLIP-based image embeddings. Experiments and ablation studies on ScanNet200 and Replica show that OpenMask3D outperforms other open-vocabulary methods, especially on the long-tail distribution. Qualitative experiments further showcase OpenMask3D’s ability to segment object properties based on free-form queries describing geometry, affordances, and materials.

We present Mix3D, a data augmentation technique for segmenting large-scale 3D scenes. Since scene context helps reasoning about object semantics, current works focus on models with large capacity and receptive fields that can fully capture the global context of an input 3D scene. However, strong contextual priors can have detrimental implications like mistaking a pedestrian crossing the street for a car. In this work, we focus on the importance of balancing global scene context and local geometry, with the goal of generalizing beyond the contextual priors in the training set. In particular, we propose a “mixing” technique which creates new training samples by combining two augmented scenes. By doing so, object instances are implicitly placed into novel out-of-context environments, therefore making it harder for models to rely on scene context alone, and instead infer semantics from local structure as well. We perform detailed analysis to understand the importance of global context, local structures and the effect of mixing scenes. In experiments, we show that models trained with Mix3D profit from a significant performance boost on indoor (ScanNet, S3DIS) and outdoor datasets (SemanticKITTI). Mix3D can be trivially used with any existing method, e.g., trained with Mix3D, MinkowskiNet outperforms all prior state-of-the-art methods by a significant margin on the ScanNet test benchmark (78.1% mIoU). Code is available at: https://nekrasov.dev/mix3d/

We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. The key idea is to optimize for detection, alignment and shape jointly over all objects in the RGB image, while focusing on realistic and physically plausible reconstructions. To this end, we propose a key-point detector that localizes objects as center points and directly predicts all object properties, including 9-DoF bounding boxes and 3D shapes – all in a single forward pass. The proposed method formulates 3D shape reconstruction as a shape selection problem, i.e. it selects among exemplar shapes from a given database. This makes it agnostic to shape representations, which enables a lightweight reconstruction of realistic and visually-pleasing shapes based on CAD-models, while the training objective is formulated around point clouds and voxel representations. A collision-loss promotes non-intersecting objects, further increasing the reconstruction realism. Given the RGB image, the presented approach performs lightweight reconstruction in a single-stage, it is real-time capable, fully differentiable and end-to-end trainable. Our experiments compare multiple approaches for 9-DoF bounding box estimation, evaluate the novel shape-selection mechanism and compare to recent methods in terms of 3D bounding box estimation and 3D shape reconstruction quality.

We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object centers. Then, we learn proposal features from grouped point features that voted for the same object center. A graph convolutional network introduces inter-proposal relations, providing higher-level feature learning in addition to the lower-level point features. Each proposal comprises a semantic label, a set of associated points over which we define a foreground-background mask, an objectness score and aggregation features. Previous works usually perform non-maximum-suppression (NMS) over proposals to obtain the final object detections or semantic instances. However, NMS can discard potentially correct predictions. Instead, our approach keeps all proposals and groups them together based on the learned aggregation features. We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.

We propose DualConvMesh-Nets (DCM-Net) a family of deep hierarchical convolutional networks over 3D geometric data that combines two types of convolutions. The first type, Geodesic convolutions, defines the kernel weights over mesh surfaces or graphs. That is, the convolutional kernel weights are mapped to the local surface of a given mesh. The second type, Euclidean convolutions, is independent of any underlying mesh structure. The convolutional kernel is applied on a neighborhood obtained from a local affinity representation based on the Euclidean distance between 3D points. Intuitively, geodesic convolutions can easily separate objects that are spatially close but have disconnected surfaces, while Euclidean convolutions can represent interactions between nearby objects better, as they are oblivious to object surfaces. To realize a multi-resolution architecture, we borrow well-established mesh simplification methods from the geometry processing domain and adapt them to define mesh-preserving pooling and unpooling operations. We experimentally show that combining both types of convolutions in our architecture leads to significant performance gains for 3D semantic segmentation, and we report competitive results on three scene segmentation benchmarks. Models and code will be made publicly available.

In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification. Point convolutions are widely used to efficiently process 3D data representations such as point clouds or graphs. However, we observe that the receptive field size of recent point convolutional networks is inherently limited. Our dilated point convolutions alleviate this issue, they significantly increase the receptive field size of point convolutions. Importantly, our dilation mechanism can easily be integrated into most existing point convolutional networks. To evaluate the resulting network architectures, we visualize the receptive field and report competitive scores on popular point cloud benchmarks.

Complementing images with inertial measurements has become one of the most popular approaches to achieve highly accurate and robust real-time camera pose tracking. In this paper, we present a keyframe-based approach to visual-inertial simultaneous localization and mapping (SLAM) for monocular and stereo cameras. Our visual-inertial SLAM system is based on a real-time capable visual-inertial odometry method that provides locally consistent trajectory and map estimates. We achieve global consistency in the estimate through online loop-closing and non-linear optimization. Furthermore, our system supports relocalization in a map that has been previously obtained and allows for continued SLAM operation. We evaluate our approach in terms of accuracy, relocalization capability and run-time efficiency on public indoor benchmark datasets and on newly recorded outdoor sequences. We demonstrate state-of-the-art performance of our system compared to a visual-inertial odometry method and baseline visual SLAM approaches in recovering the trajectory of the camera.

Inferring the pose and shape of vehicles in 3D from a movable platform still remains a challenging task due to the projective sensing principle of cameras, difficult surface properties e.g. reflections or transparency, and illumination changes between images. In this paper, we propose to use 3D shape and motion priors to regularize the estimation of the trajectory and the shape of vehicles in sequences of stereo images. We represent shapes by 3D signed distance functions and embed them in a low-dimensional manifold. Our optimization method allows for imposing a common shape across all image observations along an object track. We employ a motion model to regularize the trajectory to plausible object motions. We evaluate our method on the KITTI dataset and show state-of-the-art results in terms of shape reconstruction and pose estimation accuracy.

Most vision based systems for object tracking in urban environments focus on a limited number of important object categories such as cars or pedestrians, for which powerful detectors are available. However, practical driving scenarios contain many additional objects of interest, for which suitable detectors either do not yet exist or would be cumbersome to obtain. In this paper we propose a more general tracking approach which does not follow the often used tracking-by-detection principle. Instead, we investigate how far we can get by tracking unknown, generic objects in challenging street scenes. As such, we do not restrict ourselves to only tracking the most common categories, but are able to handle a large variety of static and moving objects. We evaluate our approach on the KITTI dataset and show competitive results for the annotated classes, even though we are not restricted to them.