Current scene flow methods broadly fail to describe motion on small objects, and current scene flow evaluation protocols hide this failure by averaging over many points, with most drawn larger objects. To fix this evaluation failure, we propose a new evaluation protocol, Bucket Normalized EPE, which is class-aware and speed-normalized, enabling contextualized error comparisons between object types that move at vastly different speeds. To highlight current method failures, we propose a frustratingly simple supervised scene flow baseline, TrackFlow, built by bolting a high-quality pretrained detector (trained using many class rebalancing techniques) onto a simple tracker, that produces state-of-the-art performance on current standard evaluations and large improvements over prior art on our new evaluation. Our results make it clear that all scene flow evaluations must be class and speed aware, and supervised scene flow methods must address point class imbalances. We release the evaluation code publicly at https://github.com/kylevedder/BucketedSceneFlowEval.
State-of-the-art lidar panoptic segmentation (LPS) methods follow bottom-up segmentation-centric fashion wherein they build upon semantic segmentation networks by utilizing clustering to obtain object instances. In this paper, we re-think this approach and propose a surprisingly simple yet effective detection-centric network for both LPS and tracking. Our network is modular by design and optimized for all aspects of both the panoptic segmentation and tracking task. One of the core components of our network is the object instance detection branch, which we train using point-level (modal) annotations, as available in segmentation-centric datasets. In the absence of amodal (cuboid) annotations, we regress modal centroids and object extent using trajectory-level supervision that provides information about object size, which cannot be inferred from single scans due to occlusions and the sparse nature of the lidar data. We obtain fine-grained instance segments by learning to associate lidar points with detected centroids. We evaluate our method on several 3D/4D LPS benchmarks and observe that our model establishes a new state-of-the-art among open-sourced models, outperforming recent query-based models.
How easy is it to sneak up on a robot? We examine whether we can detect people using only the incidental sounds they produce as they move, even when they try to be quiet. We collect a robotic dataset of high-quality 4-channel audio paired with 360 degree RGB data of people moving in different indoor settings. We train models that predict if there is a moving person nearby and their location using only audio. We implement our method on a robot, allowing it to track a single person moving quietly with only passive audio sensing. For demonstration videos, see our project page: https://sites.google.com/view/unkidnappable-robot
Mapping music to dance is a challenging problem that requires spatial and temporal coherence along with a continual synchronization with the music's progression. Taking inspiration from large language models, we introduce a 2-step approach for generating dance using a Vector Quantized-Variational Autoencoder (VQ-VAE) to distill motion into primitives and train a Transformer decoder to learn the correct sequencing of these primitives. We also evaluate the importance of music representations by comparing naive music feature extraction using Librosa to deep audio representations generated by state-of-the-art audio compression algorithms. Additionally, we train variations of the motion generator using relative and absolute positional encodings to determine the effect on generated motion quality when generating arbitrarily long sequence lengths. Our proposed approach achieve state-of-the-art results in music-to-motion generation benchmarks and enables the real-time generation of considerably longer motion sequences, the ability to chain multiple motion sequences seamlessly, and easy customization of motion sequences to meet style requirements.
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance the performance of lightweight classification models, its application to structured outputs like object detection and instance segmentation remains a complicated task, due to the variability in outputs and complex internal network modules involved in the distillation process. In this paper, we propose a simple yet surprisingly effective sequential approach to knowledge distillation that progressively transfers the knowledge of a set of teacher detectors to a given lightweight student. To distill knowledge from a highly accurate but complex teacher model, we construct a sequence of teachers to help the student gradually adapt. Our progressive strategy can be easily combined with existing detection distillation mechanisms to consistently maximize student performance in various settings. To the best of our knowledge, we are the first to successfully distill knowledge from Transformer-based teacher detectors to convolution-based students, and unprecedentedly boost the performance of ResNet-50 based RetinaNet from 36.5% to 42.0% AP and Mask R-CNN from 38.2% to 42.5% AP on the MS COCO benchmark.
LiDAR-based 3D detection plays a vital role in autonomous navigation. Surprisingly, although autonomous vehicles (AVs) must detect both near-field objects (for collision avoidance) and far-field objects (for longer-term planning), contemporary benchmarks focus only on near-field 3D detection. However, AVs must detect far-field objects for safe navigation. In this paper, we present an empirical analysis of far-field 3D detection using the long-range detection dataset Argoverse 2.0 to better understand the problem, and share the following insight: near-field LiDAR measurements are dense and optimally encoded by small voxels, while far-field measurements are sparse and are better encoded with large voxels. We exploit this observation to build a collection of range experts tuned for near-vs-far field detection, and propose simple techniques to efficiently ensemble models for long-range detection that improve efficiency by 33% and boost accuracy by 3.2% CDS.
Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds for large-scale point clouds, making them unusable as computer vision primitives for real-time applications such as open world object detection. Feed forward methods are considerably faster, running on the order of tens to hundreds of milliseconds for large-scale point clouds, but require expensive human supervision. To address both limitations, we propose Scene Flow via Distillation, a simple distillation framework that uses a label-free optimization method to produce pseudo-labels to supervise a feed forward model. Our instantiation of this framework, ZeroFlow, produces scene flow estimates in real-time on large-scale point clouds at quality competitive with state-of-the-art methods while using zero human labels. Notably, at test-time ZeroFlow is over 1000$\times$ faster than label-free state-of-the-art optimization-based methods on large-scale point clouds and over 1000$\times$ cheaper to train on unlabeled data compared to the cost of human annotation of that data. To facilitate research reuse, we release our code, trained model weights, and high quality pseudo-labels for the Argoverse 2 and Waymo Open datasets.
Neural fields have recently enjoyed great success in representing and rendering 3D scenes. However, most state-of-the-art implicit representations model static or dynamic scenes as a whole, with minor variations. Existing work on learning disentangled world and object neural fields do not consider the problem of composing objects into different world neural fields in a lighting-aware manner. We present Lighting-Aware Neural Field (LANe) for the compositional synthesis of driving scenes in a physically consistent manner. Specifically, we learn a scene representation that disentangles the static background and transient elements into a world-NeRF and class-specific object-NeRFs to allow compositional synthesis of multiple objects in the scene. Furthermore, we explicitly designed both the world and object models to handle lighting variation, which allows us to compose objects into scenes with spatially varying lighting. This is achieved by constructing a light field of the scene and using it in conjunction with a learned shader to modulate the appearance of the object NeRFs. We demonstrate the performance of our model on a synthetic dataset of diverse lighting conditions rendered with the CARLA simulator, as well as a novel real-world dataset of cars collected at different times of the day. Our approach shows that it outperforms state-of-the-art compositional scene synthesis on the challenging dataset setup, via composing object-NeRFs learned from one scene into an entirely different scene whilst still respecting the lighting variations in the novel scene. For more results, please visit our project website https://lane-composition.github.io/.
We present multimodal conditioning modules (MCM) for enabling conditional image synthesis using pretrained diffusion models. Previous multimodal synthesis works rely on training networks from scratch or fine-tuning pretrained networks, both of which are computationally expensive for large, state-of-the-art diffusion models. Our method uses pretrained networks but does not require any updates to the diffusion network's parameters. MCM is a small module trained to modulate the diffusion network's predictions during sampling using 2D modalities (e.g., semantic segmentation maps, sketches) that were unseen during the original training of the diffusion model. We show that MCM enables user control over the spatial layout of the image and leads to increased control over the image generation process. Training MCM is cheap as it does not require gradients from the original diffusion net, consists of only $\sim$1$\%$ of the number of parameters of the base diffusion model, and is trained using only a limited number of training examples. We evaluate our method on unconditional and text-conditional models to demonstrate the improved control over the generated images and their alignment with respect to the conditioning inputs.
Prior research has shown that deep models can estimate the pressure applied by a hand to a surface based on a single RGB image. Training these models requires high-resolution pressure measurements that are difficult to obtain with physical sensors. Additionally, even experts cannot reliably annotate pressure from images. Thus, data collection is a critical barrier to generalization and improved performance. We present a novel approach that enables training data to be efficiently captured from unmodified surfaces with only an RGB camera and a cooperative participant. Our key insight is that people can be prompted to perform actions that correspond with categorical labels (contact labels) describing contact pressure, such as using a specific fingertip to make low-force contact. We present ContactLabelNet, which visually estimates pressure applied by fingertips. With the use of contact labels, ContactLabelNet achieves improved performance, generalizes to novel surfaces, and outperforms models from prior work.