Learning from Demonstrations, the field that proposes to learn robot behavior models from data, is gaining popularity with the emergence of deep generative models. Although the problem has been studied for years under names such as Imitation Learning, Behavioral Cloning, or Inverse Reinforcement Learning, classical methods have relied on models that don't capture complex data distributions well or don't scale well to large numbers of demonstrations. In recent years, the robot learning community has shown increasing interest in using deep generative models to capture the complexity of large datasets. In this survey, we aim to provide a unified and comprehensive review of the last year's progress in the use of deep generative models in robotics. We present the different types of models that the community has explored, such as energy-based models, diffusion models, action value maps, or generative adversarial networks. We also present the different types of applications in which deep generative models have been used, from grasp generation to trajectory generation or cost learning. One of the most important elements of generative models is the generalization out of distributions. In our survey, we review the different decisions the community has made to improve the generalization of the learned models. Finally, we highlight the research challenges and propose a number of future directions for learning deep generative models in robotics.

We address the challenge of generating dynamic 4D scenes from monocular multi-object videos with heavy occlusions and introduce GenMOJO, a novel approach that integrates rendering-based deformable 3D Gaussian optimization with generative priors for view synthesis. While existing view-synthesis models excel at novel view generation for isolated objects, they struggle with full scenes due to their complexity and data demands. To overcome this, GenMOJO decomposes scenes into individual objects, optimizing a differentiable set of deformable Gaussians per object while capturing 2D occlusions from a 3D perspective through joint Gaussian splatting. Joint splatting ensures occlusion-aware rendering losses in observed frames, while explicit object decomposition allows the usage of object-centric diffusion models for object completion in unobserved viewpoints. To reconcile the differences between object-centric priors and the global frame-centric coordinate system of the video, GenMOJO employs differentiable transformations to unify the rendering and generative constraints within a single framework. The result is a model capable of generating 4D objects across space and time while producing 2D and 3D point tracks from monocular videos. To rigorously evaluate the quality of scene generation and the accuracy of the motion under multi-object occlusions, we introduce MOSE-PTS, a subset of the challenging MOSE benchmark, which we annotated with high-quality 2D point tracks. Quantitative evaluations and perceptual human studies confirm that GenMOJO generates more realistic novel views of scenes and produces more accurate point tracks compared to existing approaches. Project page: https://genmojo.github.io/.

Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. Recent advances in single-image depth estimation, brought about by the rise of large foundation models and the use of synthetic training data, have fueled a renewed interest in video depth. However, naively applying a single-image depth estimator to every frame of a video disregards temporal continuity, which not only leads to flickering but may also break when camera motion causes sudden changes in depth range. An obvious and principled solution would be to build on top of video foundation models, but these come with their own limitations; including expensive training and inference, imperfect 3D consistency, and stitching routines for the fixed-length (short) outputs. We take a step back and demonstrate how to turn a single-image latent diffusion model (LDM) into a state-of-the-art video depth estimator. Our model, which we call RollingDepth, has two main ingredients: (i) a multi-frame depth estimator that is derived from a single-image LDM and maps very short video snippets (typically frame triplets) to depth snippets. (ii) a robust, optimization-based registration algorithm that optimally assembles depth snippets sampled at various different frame rates back into a consistent video. RollingDepth is able to efficiently handle long videos with hundreds of frames and delivers more accurate depth videos than both dedicated video depth estimators and high-performing single-frame models. Project page: rollingdepth.github.io.

We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing point tracking methods, our approach delivers high-resolution and dense (all-pixel) correspondence fields, which can be visualized as flow maps. Unlike existing optical flow methods, our approach corresponds one frame to hundreds of subsequent frames, rather than just the next frame. We develop a new architecture for this task, blending techniques from existing work in optical flow and point tracking: the model performs iterative inference on low-resolution grids of correspondence estimates, propagating information spatially via 2D convolution layers, and propagating information temporally via pixel-aligned attention layers. The model is fast and parameter-efficient (16 million parameters), and delivers state-of-the-art point tracking accuracy at high resolution (i.e., tracking 768x1024 pixels, on a 40G GPU). A benefit of our design is that we can train jointly on optical flow datasets and point tracking datasets, and we find that doing so is crucial for top performance. We provide an extensive ablation study on our architecture details and training recipe, making it clear which details matter most. Our code and model weights are available at https://alltracker.github.io

Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric models and the rich 3D sensory data available in embodied systems. Our approach initializes most model weights from pre-trained 2D models and trains on both 2D and 3D vision-language data. We propose a novel language-conditioned mask decoder shared across 2D and 3D modalities to ground objects effectively in both RGB and RGB-D images, outperforming box-based approaches. To further reduce the domain gap between 2D and 3D, we incorporate 2D-to-3D lifting strategies, enabling UniVLG to utilize 2D data to enhance 3D performance. With these innovations, our model achieves state-of-the-art performance across multiple 3D vision-language grounding tasks, demonstrating the potential of transferring advances from 2D vision-language learning to the data-constrained 3D domain. Furthermore, co-training on both 2D and 3D data enhances performance across modalities without sacrificing 2D capabilities. By removing the reliance on 3D mesh reconstruction and ground-truth object proposals, UniVLG sets a new standard for realistic, embodied-aligned evaluation. Code and additional visualizations are available at https://univlg.github.io.

We introduce PartCrafter, the first structured 3D generative model that jointly synthesizes multiple semantically meaningful and geometrically distinct 3D meshes from a single RGB image. Unlike existing methods that either produce monolithic 3D shapes or follow two-stage pipelines, i.e. first segmenting an image and then reconstructing each segment, PartCrafter adopts a unified, compositional generation architecture that does not rely on pre-segmented inputs. Conditioned on a single image, it simultaneously denoises multiple 3D parts, enabling end-to-end part-aware generation of both individual objects and complex multi-object scenes. PartCrafter builds upon a pretrained 3D mesh diffusion transformer (DiT) trained on whole objects, inheriting the pretrained weights, encoder, and decoder, and introduces two key innovations: (1) A compositional latent space, where each 3D part is represented by a set of disentangled latent tokens; (2) A hierarchical attention mechanism that enables structured information flow both within individual parts and across all parts, ensuring global coherence while preserving part-level detail during generation. To support part-level supervision, we curate a new dataset by mining part-level annotations from large-scale 3D object datasets. Experiments show that PartCrafter outperforms existing approaches in generating decomposable 3D meshes, including parts that are not directly visible in input images, demonstrating the strength of part-aware generative priors for 3D understanding and synthesis. Code and training data are released.

Autoregressive (AR) models have long dominated the landscape of large language models, driving progress across a wide range of tasks. Recently, diffusion-based language models have emerged as a promising alternative, though their advantages over AR models remain underexplored. In this paper, we systematically study masked diffusion models in data-constrained settings—where training involves repeated passes over limited data—and find that they significantly outperform AR models when compute is abundant but data is scarce. Diffusion models make better use of repeated data, achieving lower validation loss and superior downstream performance. We find new scaling laws for diffusion models and derive a closed-form expression for the critical compute threshold at which diffusion begins to outperform AR. Finally, we explain why diffusion models excel in this regime: their randomized masking objective implicitly trains over a rich distribution of token orderings, acting as an implicit data augmentation that AR’s fixed left-to-right factorization lacks. Our results suggest that when data, not compute, is the bottleneck, diffusion models offer a compelling alternative to the standard AR paradigm. Our code is available at: https://diffusion-scaling.github.io

While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visual attention, interpret perceptual inputs, and ground abstract reasoning in spatial evidence. We introduce ViGoRL (**Vi**sually **G**r**o**unded **R**einforcement **L**earning), a vision-language model trained with RL to explicitly anchor each reasoning step to specific visual coordinates. Inspired by human visual decision-making, ViGoRL learns to produce spatially grounded reasoning traces, guiding visual attention to task-relevant regions at each step. When fine-grained exploration is required, our novel multi-turn RL framework enables the model to dynamically zoom into predicted coordinates as reasoning unfolds. Across a diverse set of visual reasoning benchmarks—including SAT-2 and BLINK for spatial reasoning, V$^\*$bench for visual search, and ScreenSpot and VisualWebArena for web-based grounding—ViGoRL consistently outperforms both supervised fine-tuning and conventional RL baselines that lack explicit grounding mechanisms. Incorporating multi-turn RL with zoomed-in visual feedback significantly improves ViGoRL’s performance on localizing small GUI elements and visual search, achieving 86.4% on V$^\*$Bench. Additionally, we find that grounding amplifies other visual behaviors such as region exploration, grounded subgoal setting, and visual verification. Finally, human evaluations show that the model’s visual references are not only spatially accurate but also helpful for understanding model reasoning steps. Our results show that visually grounded RL is a strong paradigm for imbuing models with general-purpose visual reasoning.

We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos. TAPIP3D represents videos as camera-stabilized spatio-temporal feature clouds, leveraging depth and camera motion information to lift 2D video features into a 3D world space where camera movement is effectively canceled out. Within this stabilized 3D representation, TAPIP3D iteratively refines multi-frame motion estimates, enabling robust point tracking over long time horizons. To handle the irregular structure of 3D point distributions, we propose a 3D Neighborhood-to-Neighborhood (N2N) attention mechanism—a 3D-aware contextualization strategy that builds informative, spatially coherent feature neighborhoods to support precise trajectory estimation. Our 3D-centric formulation significantly improves performance over existing 3D point tracking methods and even surpasses state-of-the-art 2D pixel trackers in accuracy when reliable depth is available. The model supports inference in both camera-centric (unstabilized) and world-centric (stabilized) coordinates, with experiments showing that compensating for camera motion leads to substantial gains in tracking robustness. By replacing the conventional 2D square correlation windows used in prior 2D and 3D trackers with a spatially grounded 3D attention mechanism, TAPIP3D achieves strong and consistent results across multiple 3D point tracking benchmarks. Our code and trained checkpoints will be public.

State-of-the-art models on contemporary 3D segmentation benchmarks like ScanNet consume and label dataset- provided 3D point clouds, obtained through post processing of sensed multiview RGB-D images. They are typically trained in-domain, forego large-scale 2D pre-training and outperform alternatives that featurize the posed RGB- D multiview images instead. The gap in performance between methods that consume posed images versus post- processed 3D point clouds has fueled the belief that 2D and 3D perception require distinct model architectures. In this paper, we challenge this view and propose ODIN (Omni-Dimensional INstance segmentation), a model that can segment and label both 2D RGB images and 3D point clouds, using a transformer architecture that alternates between 2D within-view and 3D cross-view information fusion. Our model differentiates 2D and 3D feature oper-ations through the positional encodings of the tokens in-volved, which capture pixel coordinates for 2D patch tokens and 3D coordinates for 3D feature tokens. ODIN achieves state-of-the-art performance on ScanNet200, Matterport3D and AI2THOR 3D instance segmentation benchmarks, and competitive performance on ScanNet, S3DIS and COCO. It outperforms all previous works by a wide margin when the sensed 3D point cloud is used in place of the point cloud sampled from 3D mesh. When used as the 3D perception engine in an instructable embodied agent architecture, it sets a new state-of-the-art on the TEACh action-from-dialogue benchmark. Our code and checkpoints can be found at the project website

Diffusion models excel at modeling complex and multi-modal trajectory distributions for decision-making and control. Reward-gradient guided denoising has been recently proposed to generate trajectories that maximize both a differentiable reward function and the likelihood under the data distribution captured by a diffusion model. Reward-gradient guided denoising requires a differentiable reward function fitted to both clean and noised samples, limiting its applicability as a general trajectory optimizer. In this paper, we propose Diffusion-ES, a method that combines gradient-free optimization with trajectory denoising to optimize black-box non-differentiable objectives while staying in the data manifold. Diffusion-ES samples trajectories during evolutionary search from a diffusion model and scores them using a black-box reward function. It mutates high-scoring trajecto-ries using a truncated diffusion process that applies a small number of noising and denoising steps, allowing for much more efficient exploration of the solution space. We show that Diffusion-Ex achieves state-of-the-art performance on nuPlan, an established closed-loop planning benchmark for autonomous driving. Diffusion-ES outperforms existing sampling-based planners, reactive deterministic or diffusion-based policies, and reward-gradient guidance. Additionally, we show that unlike prior guidance methods, our method can optimize non-differentiable language-shaped reward functions generated by few-shot LLM prompting. When guided by a human teacher that issues instructions to follow, our method can generate novel, highly complex behaviors, such as aggressive lane weaving, which are not present in the training data. This allows us to solve the hardest nuPlan scenarios which are beyond the capabilities of existing tra-jectory optimization methods and driving policies.11Project page: diffusion-es.github.io

We present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. RoboGen leverages the latest advancements in foundation and generative models. Instead of directly adapting these models to produce policies or low-level actions, we advocate for a generative scheme, which uses these models to automatically generate diversified tasks, scenes, and training supervisions, thereby scaling up robotic skill learning with minimal human supervision. Our approach equips a robotic agent with a self-guided propose-generate-learn cycle: the agent first proposes interesting tasks and skills to develop, and then generates simulation environments by populating pertinent assets with proper spatial configurations. Afterwards, the agent decomposes the proposed task into sub-tasks, selects the optimal learning approach (reinforcement learning, motion planning, or trajectory optimization), generates required training supervision, and then learns policies to acquire the proposed skill. Our fully generative pipeline can be queried repeatedly, producing an endless stream of skill demonstrations associated with diverse tasks and environments.

Object tracking is central to robot perception and scene understanding, allowing robots to parse a video stream in terms of moving objects with names. Tracking-by-detection has long been a dominant paradigm for object tracking of specific object categories [1], [2]. Recently, large-scale pre-trained models have shown promising advances in detecting and segmenting objects and parts in 2D static images in the wild. This raises the question: can we re-purpose these large-scale pre-trained static image models for open-vocabulary video tracking? In this paper, we combine an open-vocabulary detector [3], segmenter [4], and dense optical flow estimator [5], into a model that tracks and segments any object in 2D videos. Given a monocular video input, our method predicts object and part mask tracks with associated language descriptions, rebuilding the pipeline of Tractor [6] with modern large pre-trained models for static image detection and segmentation: we detect open-vocabulary object instances and propagate their boxes from frame to frame using a flow-based motion model, refine the propagated boxes with the box regression module of the visual detector, and prompt an open-world segmenter with the refined box to segment the objects. We decide the termination of an object track based on the objectness score of the propagated boxes as well as forward-backward optical flow consistency. We re-identify objects across occlusions using deep feature matching. We show that our model achieves strong performance on multiple established benchmarks [7], [8], [9], [10], and can produce reasonable tracks in manipulation data [11]. In particular, our model outperforms previous state-of-the-art in UVO and BURST, benchmarks for open-world object tracking and segmentation, despite never being explicitly trained for tracking. We hope that our approach can serve as a simple and extensible framework for future research and enable imitation learning from videos with unconventional objects.

Generalist robot manipulators need to learn a wide variety of manipulation skills across diverse environments. Current robot training pipelines rely on humans to provide kinesthetic demonstrations or to program simulation environments and to code up reward functions for reinforcement learning. Such human involvement is an important bottleneck towards scaling up robot learning across diverse tasks and environments. We propose Generation to Simulation (Gen2Sim), a method for scaling up robot skill learning in simulation by automating generation of 3D assets, task descriptions, task decompositions and reward functions using large pre-trained generative models of language and vision. We generate 3D assets for simulation by lifting open-world 2D object-centric images to 3D using image diffusion models and querying LLMs to determine plausible physics parameters. Given URDF files of generated and human-developed assets, we chain-of-thought prompt LLMs to map these to relevant task descriptions, temporal decompositions, and corresponding python reward functions for reinforcement learning. We show Gen2Sim succeeds in learning policies for diverse long horizon tasks, where reinforcement learning with non temporally decomposed reward functions fails. Gen2Sim provides a viable path for scaling up reinforcement learning for robot manipulators in simulation, both by diversifying and expanding task and environment development, and by facilitating the discovery of reinforcement-learned behaviors through temporal task decomposition in RL. Our work contributes hundreds of simulated assets, tasks and demonstrations, taking a step towards fully autonomous robotic manipulation skill acquisition in simulation.

Significant progress has been made in training multimodal trajectory forecasting models for autonomous driving. However, effectively integrating these models with downstream planners and model-based control approaches is still an open problem. Although these models have conventionally been evaluated for open-loop prediction, we show that they can be used to parameterize autoregressive closed-loop models without retraining. We consider recent trajectory prediction approaches which leverage learned anchor embeddings to predict multiple trajectories, finding that these anchor embeddings can parameterize discrete and distinct modes representing high-level driving behaviors. We propose to perform fully reactive closed-loop planning over these discrete latent modes, allowing us to tractably model the causal interactions between agents at each step. We validate our approach on a suite of more dynamic merging scenarios, finding that our approach avoids the frozen robot problem which is pervasive in conventional planners. Our approach also outperforms the previous state-of-the-art in CARLA on challenging dense traffic scenarios when evaluated at realistic speeds.

View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object dynamic scenes? There are two challenges in this direction: First, rendering error gradients are often insufficient to recover fast object motion, and second, view predictive generative models work much better for objects than whole scenes, so, score distillation objectives cannot currently be applied at the scene level directly. We present DreamScene4D, the first approach to generate 3D dynamic scenes of multiple objects from monocular videos via 360-degree novel view synthesis. Our key insight is a "decompose-recompose" approach that factorizes the video scene into the background and object tracks, while also factorizing object motion into 3 components: object-centric deformation, object-to-world-frame transformation, and camera motion. Such decomposition permits rendering error gradients and object view-predictive models to recover object 3D completions and deformations while bounding box tracks guide the large object movements in the scene. We show extensive results on challenging DAVIS, Kubric, and self-captured videos with quantitative comparisons and a user preference study. Besides 4D scene generation, DreamScene4D obtains accurate 2D persistent point track by projecting the inferred 3D trajectories to 2D. We will release our code and hope our work will stimulate more research on fine-grained 4D understanding from videos.

Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot in-context learning for decision making and instruction following. However, they require high-quality exemplar demonstrations to be included in their context window. In this work, we ask: Can LLMs and VLMs generate their own examples from generic, sub-optimal demonstrations? We propose In-Context Abstraction Learning (ICAL), a method that builds a memory of multimodal experience from sub-optimal demonstrations and human feedback. Given a task demonstration that may contain inefficiencies or mistakes, a VLM abstracts the trajectory into a generalized program by correcting inefficient actions and annotating cognitive abstractions: causal relationships, object state changes, temporal subgoals, and task-relevant visual elements. These abstractions are iteratively improved and adapted through human feedback while the agent attempts to execute the trajectory in a similar environment. The resulting examples, when used as exemplars in the prompt, significantly improve decision-making in retrieval-augmented LLM and VLM agents. Moreover, as the agent's library of examples grows, it becomes more efficient, relying less on human feedback and requiring fewer environment interactions per demonstration. Our ICAL agent surpasses the state-of-the-art in dialogue-based instruction following in TEACh, multimodal web agents in VisualWebArena, and action anticipation in Ego4D. In TEACh, we achieve a 12.6% improvement in goal-condition success. In VisualWebArena, our task success rate improves over the SOTA from 14.3% to 22.7% using GPT4V. In Ego4D action forecasting, we improve over few-shot GPT-4V and remain competitive with supervised models. We show finetuning our retrieval-augmented in-context agent yields additional improvements. Our approach significantly reduces reliance on manual prompt engineering and consistently outperforms in-context learning from action plans that lack such abstractions.

Current visual detectors, though impressive within their training distribution, often fail to parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation methods use auxiliary self-supervised losses to adapt the network parameters to each test example independently and have shown promising results towards generalization outside the training distribution for the task of image classification. In our work, we find evidence that these losses are insufficient for the task of scene decomposition, without also considering architectural inductive biases. Recent slot-centric generative models attempt to decompose scenes into entities in a self-supervised manner by reconstructing pixels. Drawing upon these two lines of work, we propose Slot-TTA, a semi-supervised slot-centric scene decomposition model that at test time is adapted per scene through gradient descent on reconstruction or cross-view synthesis objectives. We evaluate Slot-TTA across multiple input modalities, images or 3D point clouds, and show substantial out-of-distribution performance improvements against state-of-the-art supervised feed-forward detectors, and alternative test-time adaptation methods. Project Webpage: http://slot-tta.github.io/

Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors. Recent research has developed a variety of camera-only methods, where features are differentiably “lifted” from the multi-camera images onto the 2D ground plane, yielding a “bird's eye view” (BEV) feature representation of the 3D space around the vehicle. This line of work has produced a variety of novel “lifting” methods, but we observe that other details in the training setups have shifted at the same time, making it unclear what really matters in top-performing methods. We also observe that using cameras alone is not a real-world constraint, considering that additional sensors like radar have been integrated into real vehicles for years already. In this paper, we first of all attempt to elucidate the high-impact factors in the design and training protocol of BEV perception models. We find that batch size and input resolution greatly affect performance, while lifting strategies have a more modest effect-even a simple parameter-free lifter works well. Second, we demonstrate that radar data can provide a substantial boost to performance, helping to close the gap between camera-only and LiDAR-enabled systems. We analyze the radar usage details that lead to good performance, and invite the community to re-consider this commonly-neglected part of the sensor platform.

The alignment between deep neural network (DNN) features and cortical responses currently provides the most accurate quantitative explanation for higher visual areas. At the same time, these model features have been critiqued as uninterpretable explanations, trading one black box (the human brain) for another (a neural network). In this paper, we train networks to directly predict, from scratch, brain responses to images from a large-scale dataset of natural scenes (Allen et. al., 2021). We then use "network dissection" (Bau et. al., 2017), an explainable AI technique used for enhancing neural network interpretability by identifying and localizing the most significant features in images for individual units of a trained network, and which has been used to study category selectivity in the human brain (Khosla & Wehbe, 2022). We adapt this approach to create a hypothesis-neutral model that is then used to explore the tuning properties of specific visual regions beyond category selectivity, which we call "brain dissection". We use brain dissection to examine a range of ecologically important, intermediate properties, including depth, surface normals, curvature, and object relations across sub-regions of the parietal, lateral, and ventral visual streams, and scene-selective regions. Our findings reveal distinct preferences in brain regions for interpreting visual scenes, with ventro-lateral areas favoring closer and curvier features, medial and parietal areas opting for more varied and flatter 3D elements, and the parietal region uniquely preferring spatial relations. Scene-selective regions exhibit varied preferences, as the retrosplenial complex prefers distant and outdoor features, while the occipital and parahippocampal place areas favor proximity, verticality, and in the case of the OPA, indoor elements. Such findings show the potential of using explainable AI to uncover spatial feature selectivity across the visual cortex, contributing to a deeper, more fine-grained understanding of the functional characteristics of human visual cortex when viewing natural scenes.

We propose an unsupervised method for detecting and tracking moving objects in 3D, in unlabelled RGB-D videos. The method begins with classic handcrafted techniques for segmenting objects using motion cues: we estimate optical flow and camera motion, and conservatively segment regions that appear to be moving independently of the background. Treating these initial segments as pseudo-labels, we learn an ensemble of appearance-based 2D and 3D detectors, under heavy data augmentation. We use this ensemble to detect new instances of the "moving" type, even if they are not moving, and add these as new pseudo-labels. Our method is an expectation-maximization algorithm, where in the expectation step we fire all modules and look for agreement among them, and in the maximization step we re-train the modules to improve this agreement. The constraint of ensemble agreement helps combat contamination of the generated pseudo-labels (during the E step), and data augmentation helps the modules generalize to yetunlabelled data (during the M step). We compare against existing unsupervised object discovery and tracking methods, using challenging videos from CATER and KITTI, and show strong improvements over the state-of-the-art.

This paper explores self-supervised learning of amodal 3D feature representations from RGB and RGB-D posed images and videos, agnostic to object and scene semantic content, and evaluates the resulting scene representations in the downstream tasks of visual correspondence, object tracking, and object detection. The model infers a latent 3D representation of the scene in the form of 3D feature points, where each continuous world 3D point is mapped to its corresponding feature vector. The model is trained for contrastive view prediction by rendering 3D feature clouds in queried viewpoints and matching against the 3D feature point cloud predicted from the query view. Notably, the representation can be queried for any 3D location, even if it is not visible from the input view. Our model brings together three powerful ideas of recent exciting research work: 3D feature grids as a neural bottleneck for view prediction, implicit functions for handling resolution limitations of 3D grids, and contrastive learning for unsupervised training of feature representations. We show the resulting 3D visual feature representations effectively scale across objects and scenes, imagine information occluded or missing from the input viewpoints, track objects over time, align semantically related objects in 3D, and improve 3D object detection. We outperform many existing state-of-the-art methods for 3D feature learning and view prediction, which are either limited by 3D grid spatial resolution, do not attempt to build amodal 3D representations, or do not handle combinatorial scene variability due to their non-convolutional bottlenecks.

We propose associating language utterances to 3D visual abstractions of the scene they describe. The 3D visual abstractions are encoded as 3-dimensional visual feature maps. We infer these 3D visual scene feature maps from RGB images of the scene via view prediction: when the generated 3D scene feature map is neurally projected from a camera viewpoint, it should match the corresponding RGB image. We present generative models that condition on the dependency tree of an utterance and generate a corresponding visual 3D feature map as well as reason about its plausibility, and detector models that condition on both the dependency tree of an utterance and a related image and localize the object referents in the 3D feature map inferred from the image. Our model outperforms models of language and vision that associate language with 2D CNN activations or 2D images by a large margin in a variety of tasks, such as, classifying plausibility of utterances, detecting referential expressions, and supplying rewards for trajectory optimization of object placement policies from language instructions. We perform numerous ablations and show the improved performance of our detectors is due to its better generalization across camera viewpoints and lack of object interferences in the inferred 3D feature space, and the improved performance of our generators is due to their ability to spatially reason about objects and their configurations in 3D when mapping from language to scenes.

We propose an exploration method that incorporates lookahead search over basic learnt skills and their dynamics, and use it for reinforcement learning (RL) of manipulation policies. Our skills are multi-goal policies learned in isolation in simpler environments using existing multigoal RL formulations, analogous to options or macroactions. Coarse skill dynamics, i.e., the state transition caused by a (complete) skill execution, are learnt and are unrolled forward during lookahead search. Policy search benefits from temporal abstraction during exploration, though itself operates over low-level primitive actions, and thus the resulting policies does not suffer from suboptimality and inflexibility caused by coarse skill chaining. We show that the proposed exploration strategy results in effective learning of complex manipulation policies faster than current state-of-the-art RL methods, and converges to better policies than methods that use options or parametrized skills as building blocks of the policy itself, as opposed to guiding exploration. We show that the proposed exploration strategy results in effective learning of complex manipulation policies faster than current state-of-the-art RL methods, and converges to better policies than methods that use options or parameterized skills as building blocks of the policy itself, as opposed to guiding exploration.

We integrate two powerful ideas, geometry and deep visual representation learning, into recurrent network architectures for mobile visual scene understanding. The proposed networks learn to “lift” 2D visual features and integrate them over time into latent 3D feature maps of the scene. They are equipped with differentiable geometric operations, such as projection, unprojection, egomotion estimation and stabilization, in order to compute a geometrically-consistent mapping between the world scene and their 3D latent feature space. We train the proposed architectures to predict novel image views given short frame sequences as input. Their predictions strongly generalize to scenes with a novel number of objects, appearances and configurations, and greatly outperform predictions of previous works that do not consider egomotion stabilization or a space-aware latent feature space. We train the proposed architectures to detect and segment objects in 3D, using the latent 3D feature map as input—as opposed to 2D feature maps computed from video frames. The resulting detections are permanent: they continue to exist even when an object gets occluded or leaves the field of view. Our experiments suggest the proposed space-aware latent feature arrangement and egomotion-stabilized convolutions are essential architectural choices for spatial common sense to emerge in artificial embodied visual agents.

Humans effortlessly "program" one another by communicating goals and desires in natural language. In contrast, humans program robotic behaviours by indicating desired object locations and poses to be achieved [5], by providing RGB images of goal configurations [19], or supplying a demonstration to be imitated [17]. None of these methods generalize across environment variations, and they convey the goal in awkward technical terms. This work proposes joint learning of natural language grounding and instructable behavioural policies reinforced by perceptual detectors of natural language expressions, grounded to the sensory inputs of the robotic agent. Our supervision is narrated visual demonstrations (NVD), which are visual demonstrations paired with verbal narration (as opposed to being silent). We introduce a dataset of NVD where teachers perform activities while describing them in detail. We map the teachers' descriptions to perceptual reward detectors, and use them to train corresponding behavioural policies in simulation. We empirically show that our instructable agents (i) learn visual reward detectors using a small number of examples by exploiting hard negative mined configurations from demonstration dynamics, (ii) develop pick-and-place policies using learned visual reward detectors, (iii) benefit from object-factorized state representations that mimic the syntactic structure of natural language goal expressions, and (iv) can execute behaviours that involve novel objects in novel locations at test time, instructed by natural language.

We present recurrent geometry-aware neural networks that integrate visual in- formation across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D physical locations in the world scene and latent feature locations. Object detection, object segmentation, and 3D reconstruction is then carried out directly using the constructed 3D feature memory, as opposed to any of the input 2D images. The proposed models are equipped with differentiable egomotion-aware feature warping and (learned) depth-aware unprojection operations to achieve geometrically consistent mapping between the features in the input frame and the constructed latent model of the scene. We empirically show the proposed model generalizes much better than geometry- unaware LSTM/GRU networks, especially under the presence of multiple objects and cross-object occlusions. Combined with active view selection policies, our model learns to select informative viewpoints to integrate information from by “undoing" cross-object occlusions, seamlessly combining geometry with learning from experience.

Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images’ latent factors, or to other images, using supervised learning. Learning such mappings from unlabelled data, or improving upon supervised models by exploiting unlabelled data, remains elusive. We argue that there are two important parts to learning without annotations: (i) matching the predictions to the input observations, and (ii) matching the predictions to known priors. We propose Adversarial Inverse Graphics networks (AIGNs): weakly supervised neural network models that combine feedback from rendering their predictions, with distribution matching between their predictions and a collection of ground-truth factors. We apply AIGNs to 3D human pose estimation and 3D structure and egomotion estimation, and outperform models supervised by only paired annotations. We further apply AIGNs to facial image transformation using super-resolution and inpainting renderers, while deliberately adding biases in the ground-truth datasets. Our model seamlessly incorporates such biases, rendering input faces towards young, old, feminine, masculine or Tom Cruiselike equivalents (depending on the chosen bias), or adding lip and nose augmentations while inpainting concealed lips and noses.

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g. person segmentation, optical flow, keypoint detections etc.). Optimization models are susceptible to local minima. This has been the bottleneck that forced using clean green-screen like backgrounds at capture time, manual initialization, or switching to multiple cameras as input resource. In this work, we propose a learning based motion capture model for single camera input. Instead of optimizing mesh and skeleton parameters directly, our model optimizes neural network weights that predict 3D shape and skeleton configurations given a monocular RGB video. Our model is trained using a combination of strong supervision from synthetic data, and self-supervision from differentiable rendering of (a) skeletal keypoints, (b) dense 3D mesh motion, and (c) human-background segmentation, in an end-to-end framework. Empirically we show our model combines the best of both worlds of supervised learning and test-time optimization: supervised learning initializes the model parameters in the right regime, ensuring good pose and surface initialization at test time, without manual effort. Self-supervision by back-propagating through differentiable rendering allows (unsupervised) adaptation of the model to the test data, and offers much tighter fit than a pretrained fixed model. We show that the proposed model improves with experience and converges to low-error solutions where previous optimization methods fail.

Hierarchical feature extractors such as Convolutional Networks (ConvNets) have achieved impressive performance on a variety of classification tasks using purely feedforward processing. Feedforward architectures can learn rich representations of the input space but do not explicitly model dependencies in the output spaces, that are quite structured for tasks such as articulated human pose estimation or object segmentation. Here we propose a framework that expands the expressive power of hierarchical feature extractors to encompass both input and output spaces, by introducing top-down feedback. Instead of directly predicting the outputs in one go, we use a self-correcting model that progressively changes an initial solution by feeding back error predictions, in a process we call Iterative Error Feedback (IEF). IEF shows excellent performance on the task of articulated pose estimation in the challenging MPII and LSP benchmarks, matching the state-of-the-art without requiring ground truth scale annotation.

We segment moving objects in videos by ranking spatio-temporal segment proposals according to “moving objectness”; how likely they are to contain a moving object. In each video frame, we compute segment proposals using multiple figure-ground segmentations on per frame motion boundaries. We rank them with a Moving Objectness Detector trained on image and motion fields to detect moving objects and discard over/under segmentations or background parts of the scene. We extend the top ranked segments into spatio-temporal tubes using random walkers on motion affinities of dense point trajectories. Our final tube ranking consistently outperforms previous segmentation methods in the two largest video segmentation benchmarks currently available, for any number of proposals. Further, our per frame moving object proposals increase the detection rate up to 7% over previous state-of-the-art static proposal methods.

We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture. The ERD model is a recurrent neural network that incorporates nonlinear encoder and decoder networks before and after recurrent layers. We test instantiations of ERD architectures in the tasks of motion capture (mocap) generation, body pose labeling and body pose forecasting in videos. Our model handles mocap training data across multiple subjects and activity domains, and synthesizes novel motions while avoiding drifting for long periods of time. For human pose labeling, ERD outperforms a per frame body part detector by resolving left-right body part confusions. For video pose forecasting, ERD predicts body joint displacements across a temporal horizon of 400ms and outperforms a first order motion model based on optical flow. ERDs extend previous Long Short Term Memory (LSTM) models in the literature to jointly learn representations and their dynamics. Our experiments show such representation learning is crucial for both labeling and prediction in space-time. We find this is a distinguishing feature between the spatio-temporal visual domain in comparison to 1D text, speech or handwriting, where straightforward hard coded representations have shown excellent results when directly combined with recurrent units [31].

Human pose detectors, although successful in localising faces and torsos of people, often fail with lower arms. With fast movements body motion estimation is often inaccurate. We build a segmentation-detection algorithm that mediates the information between body parts recognition, and multi-frame motion grouping to improve both pose detection and tracking. Motion of body parts, though not accurate, is often sufficient to segment them from their backgrounds. Such segmentations are crucial for extracting hard to detect body parts out of their interior body clutter. By matching these segments to exemplars we obtain pose labeled body segments. The pose labeled segments and corresponding articulated joints are used to improve the motion flow fields by proposing kinematically constrained affine displacements on body parts. The pose-based articulated motion model is shown to handle large limb rotations and displacements. Our algorithm can detect people under rare poses, frequently missed by pose detectors, showing the benefits of jointly reasoning about pose, segmentation and motion in videos.

Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from their lifespans, has shown to outperform factorization and per frame segmentation methods for video segmentation. The scale and kinematic nature of the moving objects and the background scene determine how close or far apart trajectories are placed in the spectral embedding. Such density variations may confuse clustering algorithms, causing over-fragmentation of object interiors. Therefore, instead of clustering in the spectral embedding, we propose detecting discontinuities of embedding density between spatially neighboring trajectories. Detected discontinuities are strong indicators of object boundaries and thus valuable for video segmentation. We propose a novel embedding discretization process that recovers from over-fragmentations by merging clusters according to discontinuity evidence along inter-cluster boundaries. For segmenting articulated objects, we combine motion grouping cues with a center-surround saliency operation, resulting in “context-aware”, spatially coherent, saliency maps. Figure-ground segmentation obtained from saliency thresholding, provides object connectedness constraints that alter motion based trajectory affinities, by keeping articulated parts together and separating disconnected in time objects. Finally, we introduce Gabriel graphs as effective per frame superpixel maps for converting trajectory clustering to dense image segmentation. Gabriel edges bridge large contour gaps via geometric reasoning without over-segmenting coherent image regions. We present experimental results of our method that outperform the state-of-the-art in challenging motion segmentation datasets.

We propose a detection-free system for segmenting multiple interacting and deforming people in a video. People detectors often fail under close agent interaction, limiting the performance of detection based tracking methods. Motion information often fails to separate similarly moving agents or to group distinctly moving articulated body parts. We formulate video segmentation as graph partitioning in the trajectory domain. We classify trajectories as foreground or background based on trajectory saliencies, and use foreground trajectories as graph nodes. We incorporate object connectedness constraints into our trajectory weight matrix based on topology of foreground: we set repulsive weights between trajectories that belong to different connected components in any frame of their time intersection. Attractive weights are set between similarly moving trajectories. Information from foreground topology complements motion information and our spatiotemporal segments can be interpreted as connected moving entities rather than just trajectory groups of similar motion. All our cues are computed on trajectories and naturally encode large temporal context, which is crucial for resolving local in time ambiguities. We present results of our approach on challenging datasets outperforming by far the state of the art.