EMPERROR: A Flexible Generative Perception Error Model for Probing Self-Driving Planners

To handle the complexities of real-world traffic, learning planners for self-driving from data is a promising direction. While recent approaches have shown great progress, they typically assume a setting in which the ground-truth world state is available as input. However, when deployed, planning needs to be robust to the long-tail of errors incurred by a noisy perception system, which is often neglected in evaluation. To address this, previous work has proposed drawing adversarial samples from a perception error model (PEM) mimicking the noise characteristics of a target object detector. However, these methods use simple PEMs that fail to accurately capture all failure modes of detection. In this paper, we present EMPERROR, a novel transformer-based generative PEM, apply it to stress-test an imitation learning (IL)-based planner and show that it imitates modern detectors more faithfully than previous work. Furthermore, it is able to produce realistic noisy inputs that increase the planner's collision rate by up to 85%, demonstrating its utility as a valuable tool for a more complete evaluation of self-driving planners.

Is deeper always better? Replacing linear mappings with deep learning networks in the Discriminative Lexicon Model

Recently, deep learning models have increasingly been used in cognitive modelling of language. This study asks whether deep learning can help us to better understand the learning problem that needs to be solved by speakers, above and beyond linear methods. We utilise the Discriminative Lexicon Model (DLM, Baayen et al., 2019), which models comprehension and production with mappings between numeric form and meaning vectors. While so far, these mappings have been linear (Linear Discriminative Learning, LDL), in the present study we replace them with deep dense neural networks (Deep Discriminative Learning, DDL). We find that DDL affords more accurate mappings for large and diverse datasets from English and Dutch, but not necessarily for Estonian and Taiwan Mandarin. DDL outperforms LDL in particular for words with pseudo-morphological structure such as slend+er. Applied to average reaction times, we find that DDL is outperformed by frequency-informed linear mappings (FIL). However, DDL trained in a frequency-informed way ('frequency-informed' deep learning, FIDDL) substantially outperforms FIL. Finally, while linear mappings can very effectively be updated from trial-to-trial to model incremental lexical learning (Heitmeier et al., 2023), deep mappings cannot do so as effectively. At present, both linear and deep mappings are informative for understanding language.

RISE-SDF: a Relightable Information-Shared Signed Distance Field for Glossy Object Inverse Rendering

In this paper, we propose a novel end-to-end relightable neural inverse rendering system that achieves high-quality reconstruction of geometry and material properties, thus enabling high-quality relighting. The cornerstone of our method is a two-stage approach for learning a better factorization of scene parameters. In the first stage, we develop a reflection-aware radiance field using a neural signed distance field (SDF) as the geometry representation and deploy an MLP (multilayer perceptron) to estimate indirect illumination. In the second stage, we introduce a novel information-sharing network structure to jointly learn the radiance field and the physically based factorization of the scene. For the physically based factorization, to reduce the noise caused by Monte Carlo sampling, we apply a split-sum approximation with a simplified Disney BRDF and cube mipmap as the environment light representation. In the relighting phase, to enhance the quality of indirect illumination, we propose a second split-sum algorithm to trace secondary rays under the split-sum rendering framework.Furthermore, there is no dataset or protocol available to quantitatively evaluate the inverse rendering performance for glossy objects. To assess the quality of material reconstruction and relighting, we have created a new dataset with ground truth BRDF parameters and relighting results. Our experiments demonstrate that our algorithm achieves state-of-the-art performance in inverse rendering and relighting, with particularly strong results in the reconstruction of highly reflective objects.

Subsurface Scattering for 3D Gaussian Splatting

3D reconstruction and relighting of objects made from scattering materials present a significant challenge due to the complex light transport beneath the surface. 3D Gaussian Splatting introduced high-quality novel view synthesis at real-time speeds. While 3D Gaussians efficiently approximate an object's surface, they fail to capture the volumetric properties of subsurface scattering. We propose a framework for optimizing an object's shape together with the radiance transfer field given multi-view OLAT (one light at a time) data. Our method decomposes the scene into an explicit surface represented as 3D Gaussians, with a spatially varying BRDF, and an implicit volumetric representation of the scattering component. A learned incident light field accounts for shadowing. We optimize all parameters jointly via ray-traced differentiable rendering. Our approach enables material editing, relighting and novel view synthesis at interactive rates. We show successful application on synthetic data and introduce a newly acquired multi-view multi-light dataset of objects in a light-stage setup. Compared to previous work we achieve comparable or better results at a fraction of optimization and rendering time while enabling detailed control over material attributes. Project page https://sss.jdihlmann.com/

DualAD: Disentangling the Dynamic and Static World for End-to-End Driving

State-of-the-art approaches for autonomous driving integrate multiple sub-tasks of the overall driving task into a single pipeline that can be trained in an end-to-end fashion by passing latent representations between the different modules. In contrast to previous approaches that rely on a unified grid to represent the belief state of the scene, we propose dedicated representations to disentangle dynamic agents and static scene elements. This allows us to explicitly compensate for the effect of both ego and object motion between consecutive time steps and to flexibly propagate the belief state through time. Furthermore, dynamic objects can not only attend to the input camera images, but also directly benefit from the inferred static scene structure via a novel dynamic-static cross-attention. Extensive experiments on the challenging nuScenes benchmark demonstrate the benefits of the proposed dual-stream design, especially for modelling highly dynamic agents in the scene, and highlight the improved temporal consistency of our approach. Our method titled DualAD not only outperforms independently trained single-task networks, but also improves over previous state-of-the-art end-to-end models by a large margin on all tasks along the functional chain of driving.

Iterative Cluster Harvesting for Wafer Map Defect Patterns

Unsupervised clustering of wafer map defect patterns is challenging because the appearance of certain defect patterns varies significantly. This includes changing shape, location, density, and rotation of the defect area on the wafer. We present a harvesting approach, which can cluster even challenging defect patterns of wafer maps well. Our approach makes use of a well-known, three-step procedure: feature extraction, dimension reduction, and clustering. The novelty in our approach lies in repeating dimensionality reduction and clustering iteratively while filtering out one cluster per iteration according to its silhouette score. This method leads to an improvement of clustering performance in general and is especially useful for difficult defect patterns. The low computational effort allows for a quick assessment of large datasets and can be used to support manual labeling efforts. We benchmark against related approaches from the literature and show improved results on a real-world industrial dataset.

Disentangling representations of retinal images with generative models

Retinal fundus images play a crucial role in the early detection of eye diseases and, using deep learning approaches, recent studies have even demonstrated their potential for detecting cardiovascular risk factors and neurological disorders. However, the impact of technical factors on these images can pose challenges for reliable AI applications in ophthalmology. For example, large fundus cohorts are often confounded by factors like camera type, image quality or illumination level, bearing the risk of learning shortcuts rather than the causal relationships behind the image generation process. Here, we introduce a novel population model for retinal fundus images that effectively disentangles patient attributes from camera effects, thus enabling controllable and highly realistic image generation. To achieve this, we propose a novel disentanglement loss based on distance correlation. Through qualitative and quantitative analyses, we demonstrate the effectiveness of this novel loss function in disentangling the learned subspaces. Our results show that our model provides a new perspective on the complex relationship between patient attributes and technical confounders in retinal fundus image generation.

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

We present SHINOBI, an end-to-end framework for the reconstruction of shape, material, and illumination from object images captured with varying lighting, pose, and background. Inverse rendering of an object based on unconstrained image collections is a long-standing challenge in computer vision and graphics and requires a joint optimization over shape, radiance, and pose. We show that an implicit shape representation based on a multi-resolution hash encoding enables faster and robust shape reconstruction with joint camera alignment optimization that outperforms prior work. Further, to enable the editing of illumination and object reflectance (i.e. material) we jointly optimize BRDF and illumination together with the object's shape. Our method is class-agnostic and works on in-the-wild image collections of objects to produce relightable 3D assets for several use cases such as AR/VR, movies, games, etc. Project page: https://shinobi.aengelhardt.com Video: https://www.youtube.com/watch?v=iFENQ6AcYd8&feature=youtu.be

Zero-shot Translation of Attention Patterns in VQA Models to Natural Language

Converting a model's internals to text can yield human-understandable insights about the model. Inspired by the recent success of training-free approaches for image captioning, we propose ZS-A2T, a zero-shot framework that translates the transformer attention of a given model into natural language without requiring any training. We consider this in the context of Visual Question Answering (VQA). ZS-A2T builds on a pre-trained large language model (LLM), which receives a task prompt, question, and predicted answer, as inputs. The LLM is guided to select tokens which describe the regions in the input image that the VQA model attended to. Crucially, we determine this similarity by exploiting the text-image matching capabilities of the underlying VQA model. Our framework does not require any training and allows the drop-in replacement of different guiding sources (e.g. attribution instead of attention maps), or language models. We evaluate this novel task on textual explanation datasets for VQA, giving state-of-the-art performances for the zero-shot setting on GQA-REX and VQA-X. Our code is available at: https://github.com/ExplainableML/ZS-A2T.

ViPE: Visualise Pretty-much Everything

Figurative and non-literal expressions are profoundly integrated in human communication. Visualising such expressions allow us to convey our creative thoughts, and evoke nuanced emotions. Recent text-to-image models like Stable Diffusion, on the other hand, struggle to depict non-literal expressions. Recent works primarily deal with this issue by compiling humanly annotated datasets on a small scale, which not only demands specialised expertise but also proves highly inefficient. To address this issue, we introduce ViPE: Visualise Pretty-much Everything. ViPE offers a series of lightweight and robust language models that have been trained on a large-scale set of lyrics with noisy visual descriptions that represent their implicit meaning. The synthetic visual descriptions are generated by GPT3.5 relying on neither human annotations nor images. ViPE effectively expresses any arbitrary piece of text into a visualisable description, enabling meaningful and high-quality image generation. We provide compelling evidence that ViPE is more robust than GPT3.5 in synthesising visual elaborations. ViPE also exhibits an understanding of figurative expressions comparable to human experts, providing a powerful and open-source backbone to many downstream applications such as music video and caption generation.