Objects make unique sounds under different perturbations, environment conditions, and poses relative to the listener. While prior works have modeled impact sounds and sound propagation in simulation, we lack a standard dataset of impact sound fields of real objects for audio-visual learning and calibration of the sim-to-real gap. We present RealImpact, a large-scale dataset of real object impact sounds recorded under controlled conditions. RealImpact contains 150,000 recordings of impact sounds of 50 everyday objects with detailed annotations, including their impact locations, microphone locations, contact force profiles, material labels, and RGBD images. We make preliminary attempts to use our dataset as a reference to current simulation methods for estimating object impact sounds that match the real world. Moreover, we demonstrate the usefulness of our dataset as a testbed for acoustic and audio-visual learning via the evaluation of two benchmark tasks, including listener location classification and visual acoustic matching.
Learned visual dynamics models have proven effective for robotic manipulation tasks. Yet, it remains unclear how best to represent scenes involving multi-object interactions. Current methods decompose a scene into discrete objects, but they struggle with precise modeling and manipulation amid challenging lighting conditions as they only encode appearance tied with specific illuminations. In this work, we propose using object-centric neural scattering functions (OSFs) as object representations in a model-predictive control framework. OSFs model per-object light transport, enabling compositional scene re-rendering under object rearrangement and varying lighting conditions. By combining this approach with inverse parameter estimation and graph-based neural dynamics models, we demonstrate improved model-predictive control performance and generalization in compositional multi-object environments, even in previously unseen scenarios and harsh lighting conditions.
Embodied AI agents that search for objects in large environments such as households often need to make efficient decisions by predicting object locations based on partial information. We pose this as a new type of link prediction problem: link prediction on partially observable dynamic graphs. Our graph is a representation of a scene in which rooms and objects are nodes, and their relationships are encoded in the edges; only parts of the changing graph are known to the agent at each timestep. This partial observability poses a challenge to existing link prediction approaches, which we address. We propose a novel state representation -- Scene Graph Memory (SGM) -- with captures the agent's accumulated set of observations, as well as a neural net architecture called a Node Edge Predictor (NEP) that extracts information from the SGM to search efficiently. We evaluate our method in the Dynamic House Simulator, a new benchmark that creates diverse dynamic graphs following the semantic patterns typically seen at homes, and show that NEP can be trained to predict the locations of objects in a variety of environments with diverse object movement dynamics, outperforming baselines both in terms of new scene adaptability and overall accuracy. The codebase and more can be found at https://www.scenegraphmemory.com.
Recent advances in self-supervised representation learning have enabled more efficient and robust model performance without relying on extensive labeled data. However, most works are still focused on images, with few working on videos and even fewer on multi-view videos, where more powerful inductive biases can be leveraged for self-supervision. In this work, we propose a novel method for representation learning of multi-view videos, where we explicitly model the representation space to maintain Homography Equivariance (HomE). Our method learns an implicit mapping between different views, culminating in a representation space that maintains the homography relationship between neighboring views. We evaluate our HomE representation via action recognition and pedestrian intent prediction as downstream tasks. On action classification, our method obtains 96.4% 3-fold accuracy on the UCF101 dataset, better than most state-of-the-art self-supervised learning methods. Similarly, on the STIP dataset, we outperform the state-of-the-art by 6% for pedestrian intent prediction one second into the future while also obtaining an accuracy of 91.2% for pedestrian action (cross vs. not-cross) classification. Code is available at https://github.com/anirudhs123/HomE.
We introduce the ObjectFolder Benchmark, a benchmark suite of 10 tasks for multisensory object-centric learning, centered around object recognition, reconstruction, and manipulation with sight, sound, and touch. We also introduce the ObjectFolder Real dataset, including the multisensory measurements for 100 real-world household objects, building upon a newly designed pipeline for collecting the 3D meshes, videos, impact sounds, and tactile readings of real-world objects. We conduct systematic benchmarking on both the 1,000 multisensory neural objects from ObjectFolder, and the real multisensory data from ObjectFolder Real. Our results demonstrate the importance of multisensory perception and reveal the respective roles of vision, audio, and touch for different object-centric learning tasks. By publicly releasing our dataset and benchmark suite, we hope to catalyze and enable new research in multisensory object-centric learning in computer vision, robotics, and beyond. Project page: https://objectfolder.stanford.edu
Developing embodied agents in simulation has been a key research topic in recent years. Exciting new tasks, algorithms, and benchmarks have been developed in various simulators. However, most of them assume deaf agents in silent environments, while we humans perceive the world with multiple senses. We introduce Sonicverse, a multisensory simulation platform with integrated audio-visual simulation for training household agents that can both see and hear. Sonicverse models realistic continuous audio rendering in 3D environments in real-time. Together with a new audio-visual VR interface that allows humans to interact with agents with audio, Sonicverse enables a series of embodied AI tasks that need audio-visual perception. For semantic audio-visual navigation in particular, we also propose a new multi-task learning model that achieves state-of-the-art performance. In addition, we demonstrate Sonicverse's realism via sim-to-real transfer, which has not been achieved by other simulators: an agent trained in Sonicverse can successfully perform audio-visual navigation in real-world environments. Sonicverse is available at: https://github.com/StanfordVL/Sonicverse.
In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these sources, inductive biases take a paramount role in enabling disentanglement. In this work, we construct an inductive bias towards compositionally encoding and decoding data by enforcing a harsh communication bottleneck. Concretely, we do this by (i) quantizing the latent space into learnable discrete codes with a separate scalar codebook per dimension and (ii) applying strong model regularization via an unusually high weight decay. Intuitively, the quantization forces the encoder to use a small number of latent values across many datapoints, which in turn enables the decoder to assign a consistent meaning to each value. Regularization then serves to drive the model towards this parsimonious strategy. We demonstrate the broad applicability of this approach by adding it to both basic data-reconstructing (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models. In order to reliably assess these models, we also propose InfoMEC, new metrics for disentanglement that are cohesively grounded in information theory and fix well-established shortcomings in previous metrics. Together with regularization, latent quantization dramatically improves the modularity and explicitness of learned representations on a representative suite of benchmark datasets. In particular, our quantized-latent autoencoder (QLAE) consistently outperforms strong methods from prior work in these key disentanglement properties without compromising data reconstruction.
Establishing correspondence between images or scenes is a significant challenge in computer vision, especially given occlusions, viewpoint changes, and varying object appearances. In this paper, we present Siamese Masked Autoencoders (SiamMAE), a simple extension of Masked Autoencoders (MAE) for learning visual correspondence from videos. SiamMAE operates on pairs of randomly sampled video frames and asymmetrically masks them. These frames are processed independently by an encoder network, and a decoder composed of a sequence of cross-attention layers is tasked with predicting the missing patches in the future frame. By masking a large fraction ($95\%$) of patches in the future frame while leaving the past frame unchanged, SiamMAE encourages the network to focus on object motion and learn object-centric representations. Despite its conceptual simplicity, features learned via SiamMAE outperform state-of-the-art self-supervised methods on video object segmentation, pose keypoint propagation, and semantic part propagation tasks. SiamMAE achieves competitive results without relying on data augmentation, handcrafted tracking-based pretext tasks, or other techniques to prevent representational collapse.
Recent advancements in multimodal pre-training methods have shown promising efficacy in 3D representation learning by aligning multimodal features across 3D shapes, their 2D counterparts, and language descriptions. However, the methods used by existing multimodal pre-training frameworks to gather multimodal data for 3D applications lack scalability and comprehensiveness, potentially constraining the full potential of multimodal learning. The main bottleneck lies in the language modality's scalability and comprehensiveness. To address this, we introduce ULIP-2, a tri-modal pre-training framework that leverages state-of-the-art large multimodal models to automatically generate holistic language counterparts for 3D objects. It does not require any 3D annotations, and is therefore scalable to large datasets. We conduct experiments on two large-scale 3D datasets, Objaverse and ShapeNet, and augment them with tri-modal datasets of 3D point clouds, images, and language for training ULIP-2. ULIP-2 achieves significant improvements on downstream zero-shot classification on ModelNet40 (74.0% in top-1 accuracy); on the real-world ScanObjectNN benchmark, it obtains 91.5% in overall accuracy with only 1.4 million parameters, signifying a breakthrough in scalable multimodal 3D representation learning without human 3D annotations. The code, along with the generated tri-modal datasets, can be found at https://github.com/salesforce/ULIP.
In order to build artificial intelligence systems that can perceive and reason with human behavior in the real world, we must first design models that conduct complex spatio-temporal reasoning over motion sequences. Moving towards this goal, we propose the HumanMotionQA task to evaluate complex, multi-step reasoning abilities of models on long-form human motion sequences. We generate a dataset of question-answer pairs that require detecting motor cues in small portions of motion sequences, reasoning temporally about when events occur, and querying specific motion attributes. In addition, we propose NSPose, a neuro-symbolic method for this task that uses symbolic reasoning and a modular design to ground motion through learning motion concepts, attribute neural operators, and temporal relations. We demonstrate the suitability of NSPose for the HumanMotionQA task, outperforming all baseline methods.