Yizhe WU

Yizhe Wu, Oiwi Parker Jones, Ingmar Posner

We present ObPose, an unsupervised object-centric inference and generation model which learns 3D-structured latent representations from RGB-D scenes. Inspired by prior art in 2D representation learning, ObPose considers a factorised latent space, separately encoding object location (where) and appearance (what). ObPose further leverages an object's pose (i.e. location and orientation), defined via a minimum volume principle, as a novel inductive bias for learning the where component. To achieve this, we propose an efficient, voxelised approximation approach to recover the object shape directly from a neural radiance field (NeRF). As a consequence, ObPose models each scene as a composition of NeRFs, richly representing individual objects. To evaluate the quality of the learned representations, ObPose is evaluated quantitatively on the YCB, MultiShapeNet, and CLEVR datatasets for unsupervised scene segmentation, outperforming the current state-of-the-art in 3D scene inference (ObSuRF) by a significant margin. Generative results provide qualitative demonstration that the same ObPose model can both generate novel scenes and flexibly edit the objects in them. These capacities again reflect the quality of the learned latents and the benefits of disentangling the where and what components of a scene. Key design choices made in the ObPose encoder are validated with ablations.

Pan Wang, Yang Liu, Guile Wu et al.

4D spatial intelligence involves perceiving and processing how objects move or change over time. Humans naturally possess 4D spatial intelligence, supporting a broad spectrum of spatial reasoning abilities. To what extent can Multimodal Large Language Models (MLLMs) achieve human-level 4D spatial intelligence? In this work, we present Spatial4D-Bench, a versatile 4D spatial intelligence benchmark designed to comprehensively assess the 4D spatial reasoning abilities of MLLMs. Unlike existing spatial intelligence benchmarks that are often small-scale or limited in diversity, Spatial4D-Bench provides a large-scale, multi-task evaluation benchmark consisting of ~40,000 question-answer pairs covering 18 well-defined tasks. We systematically organize these tasks into six cognitive categories: object understanding, scene understanding, spatial relationship understanding, spatiotemporal relationship understanding, spatial reasoning and spatiotemporal reasoning. Spatial4D-Bench thereby offers a structured and comprehensive benchmark for evaluating the spatial cognition abilities of MLLMs, covering a broad spectrum of tasks that parallel the versatility of human spatial intelligence. We benchmark various state-of-the-art open-source and proprietary MLLMs on Spatial4D-Bench and reveal their substantial limitations in a wide variety of 4D spatial reasoning aspects, such as route plan, action recognition, and physical plausibility reasoning. We hope that the findings provided in this work offer valuable insights to the community and that our benchmark can facilitate the development of more capable MLLMs toward human-level 4D spatial intelligence. More resources can be found on our project page.

Fusang Wang, Hala Djeghim, Nathan Piasco et al.

Reconstructing the surrounding surface geometry from recorded driving sequences poses a significant challenge due to the limited image overlap and complex topology of urban environments. SoTA neural implicit surface reconstruction methods often struggle in such setting, either failing due to small vision overlap or exhibiting suboptimal performance in accurately reconstructing both the surface and fine structures. To address these limitations, we introduce J-NeuS, a novel hybrid implicit surface reconstruction method for large driving sequences with outward facing camera poses. J-NeuS cross-representation uncertainty estimation to tackle ambiguous geometry caused by limited observations. Our method performs joint optimization of two radiance fields in addition to guided sampling achieving accurate reconstruction of large areas along with fine structures in complex urban scenarios. Extensive evaluation on major driving datasets demonstrates the superiority of our approach in reconstructing large driving sequences with limited image overlap, outperforming concurrent SoTA methods.

Yizhe Wu, Oiwi Parker Jones, Martin Engelcke et al.

Recent advances in unsupervised learning for object detection, segmentation, and tracking hold significant promise for applications in robotics. A common approach is to frame these tasks as inference in probabilistic latent-variable models. In this paper, however, we show that the current state-of-the-art struggles with visually complex scenes such as typically encountered in robot manipulation tasks. We propose APEX, a new latent-variable model which is able to segment and track objects in more realistic scenes featuring objects that vary widely in size and texture, including the robot arm itself. This is achieved by a principled mask normalisation algorithm and a high-resolution scene encoder. To evaluate our approach, we present results on the real-world Sketchy dataset. This dataset, however, does not contain ground truth masks and object IDs for a quantitative evaluation. We thus introduce the Panda Pushing Dataset (P2D) which shows a Panda arm interacting with objects on a table in simulation and which includes ground-truth segmentation masks and object IDs for tracking. In both cases, APEX comprehensively outperforms the current state-of-the-art in unsupervised object segmentation and tracking. We demonstrate the efficacy of our segmentations for robot skill execution on an object arrangement task, where we also achieve the best or comparable performance among all the baselines.

Chia-Man Hung, Li Sun, Yizhe Wu et al.

End-to-end visuomotor control is emerging as a compelling solution for robot manipulation tasks. However, imitation learning-based visuomotor control approaches tend to suffer from a common limitation, lacking the ability to recover from an out-of-distribution state caused by compounding errors. In this paper, instead of using tactile feedback or explicitly detecting the failure through vision, we investigate using the uncertainty of a policy neural network. We propose a novel uncertainty-based approach to detect and recover from failure cases. Our hypothesis is that policy uncertainties can implicitly indicate the potential failures in the visuomotor control task and that robot states with minimum uncertainty are more likely to lead to task success. To recover from high uncertainty cases, the robot monitors its uncertainty along a trajectory and explores possible actions in the state-action space to bring itself to a more certain state. Our experiments verify this hypothesis and show a significant improvement on task success rate: 12% in pushing, 15% in pick-and-reach and 22% in pick-and-place.

Yizhe Wu, Sudhanshu Kasewa, Oliver Groth et al.

In this paper we explore the richness of information captured by the latent space of a vision-based generative model. The model combines unsupervised generative learning with a task-based performance predictor to learn and to exploit task-relevant object affordances given visual observations from a reaching task, involving a scenario and a stick-like tool. While the learned embedding of the generative model captures factors of variation in 3D tool geometry (e.g. length, width, and shape), the performance predictor identifies sub-manifolds of the embedding that correlate with task success. Within a variety of scenarios, we demonstrate that traversing the latent space via backpropagation from the performance predictor allows us to imagine tools appropriate for the task at hand. Our results indicate that affordances-like the utility for reaching-are encoded along smooth trajectories in latent space. Accessing these emergent affordances by considering only high-level performance criteria (such as task success) enables an agent to manipulate tool geometries in a targeted and deliberate way.